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

    Neuronpedia

    INDEX
    Explanations

    tokens related to header formatting in programming or documentation

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

    Code snippets and special characters

    np_acts-logits-general · gemini-2.0-flash

    genetic or IL-23

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    -0.64
     in
    -0.63
     to
    -0.60
     a
    -0.59
    :
    -0.57
     —
    -0.57
    ,
    -0.56
    fortawesome
    -0.55
     from
    -0.51
    ofType
    -0.51
    POSITIVE LOGITS
     pleaſure
    1.11
     itſelf
    1.02
     للمعارف
    0.96
     purpoſe
    0.94
     Majefty
    0.93
     greateſt
    0.92
     myſelf
    0.91
    kloped
    0.90
     moschino
    0.88
     raiſ
    0.88
    Act Density 0.305%

    No Known Activations