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

    Neuronpedia

    INDEX
    Explanations

    references to criminal history and related legal categories

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

    criminal legal proceedings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tiết
    -0.44
    itario
    -0.42
    uticos
    -0.41
    MetaObject
    -0.41
     dig
    -0.40
    丈
    -0.40
    […]
    -0.40
     postural
    -0.39
     flap
    -0.38
    blatt
    -0.38
    POSITIVE LOGITS
     Crime
    0.91
    Criminal
    0.89
     Criminal
    0.88
    criminal
    0.87
     crime
    0.86
     criminal
    0.85
     CRIMINAL
    0.85
     criminality
    0.85
     CRIME
    0.84
    crime
    0.82
    Act Density 0.019%

    No Known Activations