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

    Neuronpedia

    INDEX
    Explanations

    references to illegal activities or actions

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

    illegal acts and circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.57
    InputBorder
    -0.55
    volezza
    -0.54
     Dimensiones
    -0.53
    paraíso
    -0.52
     abordagem
    -0.51
     mogelijkheden
    -0.50
    CardView
    -0.50
     AssemblyTitle
    -0.49
     betrekking
    -0.49
    POSITIVE LOGITS
     illegal
    1.73
    illegal
    1.52
     Illegal
    1.51
    Illegal
    1.36
     illegally
    1.30
     ilegal
    1.28
     illeg
    1.15
     unlawful
    1.05
     illicit
    0.96
     ileg
    0.95
    Act Density 0.011%

    No Known Activations