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

    Neuronpedia

    INDEX
    Explanations

    terms related to illegal activities or immigration laws

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

    illegal arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carriera
    -0.40
     substanti
    -0.37
     prominent
    -0.35
    зопас
    -0.34
    GeneratedMessage
    -0.34
    Warmly
    -0.34
    addContainerGap
    -0.33
    rrggbb
    -0.33
    最快更新
    -0.33
    MessageOf
    -0.33
    POSITIVE LOGITS
     illegal
    0.95
    illegal
    0.91
    Illegal
    0.87
     Illegal
    0.86
     illegally
    0.85
     ilegal
    0.81
     unlawful
    0.79
     illegitimate
    0.74
     illicit
    0.68
     unlawfully
    0.68
    Act Density 0.039%

    No Known Activations