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

    Neuronpedia

    INDEX
    Explanations

    words related to financial crime detection and prevention

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

    illegal or unauthorized actions

    np_acts-logits-general · gemini-2.0-flash

    breaking laws or rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.90
    GeoNames
    -0.57
    Surviving
    -0.55
     dAtA
    -0.55
    følgelig
    -0.53
     JAXBElement
    -0.53
     chofe
    -0.53
     WaitFor
    -0.53
    ArgsConstructor
    -0.52
    ंदीखरीदारी
    -0.52
    POSITIVE LOGITS
     illegally
    1.87
     illegal
    1.73
     unauthorized
    1.52
    illegal
    1.47
     unlawfully
    1.46
     violation
    1.45
     violate
    1.37
     unlawful
    1.36
     ilegal
    1.35
     незакон
    1.32
    Act Density 0.839%

    No Known Activations