Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to various issues and operational matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following broad topics/nouns

    np_acts-logits-general · gemini-2.0-flash

    issues related to settings

    np_acts-logits-general · gemini-2.5-flash-lite

    general nouns referring to comprehensive topics, collections, or categories.

    oai_token-act-pair · claude-4-5-haikuTriggered by @johnny
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.66
     TestBed
    -0.63
     duquel
    -0.54
    </tfoot>
    -0.53
    bebasan
    -0.52
    hoeddwyd
    -0.52
    setContentView
    -0.51
    ỡng
    -0.51
    ConstraintMaker
    -0.51
     NSCoder
    -0.49
    POSITIVE LOGITS
     related
    2.60
    related
    2.08
     relating
    2.07
     associated
    1.95
     Related
    1.91
     relacionado
    1.79
     pertaining
    1.75
     RELATED
    1.74
    Related
    1.73
     relacionados
    1.68
    Act Density 0.715%

    No Known Activations