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

    Neuronpedia

    INDEX
    Explanations

    references to hazardous or toxic substances and situations

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

    hazardous substances or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ervlak
    -0.53
    horabuena
    -0.46
    MeasureSpec
    -0.43
    TProtocol
    -0.43
    InjectAttribute
    -0.42
    ołnier
    -0.42
     laiko
    -0.42
     Platz
    -0.42
    Platz
    -0.41
    CopyWith
    -0.41
    POSITIVE LOGITS
     Hazardous
    0.91
     hazardous
    0.87
    Hazardous
    0.80
    hazardous
    0.73
     dangerous
    0.66
     Toxic
    0.65
     toxic
    0.60
    Toxic
    0.58
     chemicals
    0.56
     Dangerous
    0.56
    Act Density 0.002%

    No Known Activations