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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal activity and legal implications

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

    criminal acts and illegality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ddots
    -0.36
     princesas
    -0.35
    WebVitals
    -0.35
     ligera
    -0.34
    RTLD
    -0.34
     favoriser
    -0.34
    ソール
    -0.33
     navideña
    -0.33
     cancha
    -0.33
    pædia
    -0.33
    POSITIVE LOGITS
     criminal
    0.79
     crime
    0.78
    criminal
    0.75
     criminality
    0.72
     Criminal
    0.71
     Crime
    0.70
     Crimin
    0.69
    Criminal
    0.68
     illegal
    0.67
     Illegal
    0.66
    Act Density 0.152%

    No Known Activations