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

    Neuronpedia

    INDEX
    Explanations

    crime

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of specific criminal offenses or legal charges (e.g. “rebellion,” “treason”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Patton
    -0.07
    Metadata
    -0.06
    sert
    -0.06
    (kv
    -0.06
    �
    -0.06
     Hazard
    -0.06
    subtotal
    -0.06
    turtle
    -0.06
    RC
    -0.06
    .tmp
    -0.06
    POSITIVE LOGITS
     Joi
    0.07
     Broadcom
    0.07
     kể
    0.07
     بیرون
    0.06
     왜
    0.06
    (Of
    0.06
     Meal
    0.06
     đầy
    0.06
    -shadow
    0.06
    ืน
    0.06
    Act Density 0.050%

    No Known Activations