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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

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

    Follows a period and then a letter

    np_acts-logits-general · gemini-2.0-flash

    P.S. or S. followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.73
    DockStyle
    -0.61
    readFileSync
    -0.60
     Stays
    -0.58
    MessageOf
    -0.55
    Referințe
    -0.55
     باخ
    -0.54
    WithIOException
    -0.54
    ölker
    -0.53
     批
    -0.53
    POSITIVE LOGITS
    BeginContext
    0.64
     autorytatywna
    0.62
    ArgsConstructor
    0.52
    PerformLayout
    0.52
    Cubit
    0.51
    ოლი
    0.46
     InputDecoration
    0.45
    lognese
    0.45
     wegen
    0.45
    lgari
    0.45
    Act Density 0.229%

    No Known Activations