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

    Neuronpedia

    INDEX
    Explanations

    the beginning of significant sections or topics in a text

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

    Still, despite, laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anyahu
    -0.68
     =>
    -0.66
     alſo
    -0.66
    URLException
    -0.65
     relâche
    -0.65
     sẻ
    -0.63
    LookAnd
    -0.63
    tahui
    -0.63
    MeasureSpec
    -0.63
     propOrder
    -0.63
    POSITIVE LOGITS
     Still
    0.96
    Still
    0.95
     still
    0.94
    still
    0.91
     STILL
    0.78
    STILL
    0.77
     Aún
    0.76
     pořád
    0.72
     malgré
    0.71
     spite
    0.70
    Act Density 0.122%

    No Known Activations