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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases expressing hypotheses or conjectures

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

    statements or remarks

    np_acts-logits-general · gemini-2.0-flash

    explained above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.89
     estekak
    -0.85
    ScopeManager
    -0.83
    Brainz
    -0.76
     resourceCulture
    -0.76
    .*")]
    -0.74
    IsContent
    -0.73
    رشف
    -0.71
    Autoritní
    -0.70
    yarnpkg
    -0.70
    POSITIVE LOGITS
     noted
    0.69
     apologe
    0.58
     conjecture
    0.58
     reported
    0.57
     note
    0.56
     remark
    0.55
    κτηρισ
    0.51
     question
    0.51
     stated
    0.50
     belirt
    0.50
    Act Density 0.224%

    No Known Activations