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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating device efficiency and performance metrics

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

    qualifiers and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.62
    IndentedString
    -0.57
    SharedCtor
    -0.56
    Diweddarwch
    -0.53
     jadx
    -0.52
    setVerticalGroup
    -0.51
     '\\;'
    -0.51
    principalColumn
    -0.47
    HasColumnType
    -0.47
     arşivlendi
    -0.46
    POSITIVE LOGITS
     knock
    0.41
     Knock
    0.38
    你看
    0.38
     afford
    0.36
     Kill
    0.35
    メン
    0.35
    bParam
    0.35
    气
    0.34
     dipa
    0.34
     KILL
    0.34
    Act Density 0.582%

    No Known Activations