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

    Neuronpedia

    INDEX
    Explanations

    crimes and impunity

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases describing legal outcomes—especially escaping or avoiding punishment (e.g. “escape justice,” probation, free man).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    EndDate
    -0.07
    <R
    -0.07
     resurrection
    -0.06
    din
    -0.06
     perf
    -0.06
     Preserve
    -0.06
     captivating
    -0.06
     altar
    -0.06
    591
    -0.06
     turnover
    -0.06
    POSITIVE LOGITS
     isError
    0.07
     quo
    0.07
    े.
    0.07
     schon
    0.07
     containerView
    0.06
     nás
    0.06
    ình
    0.06
    抜
    0.06
    าก
    0.06
     예정
    0.06
    Act Density 0.036%

    No Known Activations