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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical or geometrical concepts and relationships

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

    before "qu", "ni", "iss" or "eks"

    np_acts-logits-general · gemini-2.0-flash

    colloquy, Verzeichnisschutz, connaissais

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.76
     in
    -0.72
    ing
    -0.68
     (
    -0.68
    ers
    -0.66
    .
    -0.66
    es
    -0.65
     and
    -0.62
    -
    -0.62
    :
    -0.62
    POSITIVE LOGITS
    ſelves
    1.63
    ſelf
    1.61
     myſelf
    1.51
     ſind
    1.49
     ſche
    1.41
     ་་
    1.40
     Anſ
    1.39
     itſelf
    1.39
     pleaſure
    1.36
     ſeveral
    1.35
    Act Density 0.215%

    No Known Activations