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

    Neuronpedia

    INDEX
    Explanations

    crimes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ịch
    -0.08
    �
    -0.08
     melanch
    -0.07
    使我
    -0.07
    _CLICK
    -0.07
     pond
    -0.06
    _AST
    -0.06
    สง
    -0.06
    темпер
    -0.06
     libert
    -0.06
    POSITIVE LOGITS
    <k
    0.07
    ᗜ
    0.07
    뼈
    0.07
     lạ
    0.07
    不远处
    0.07
     מוכר
    0.07
    برز
    0.07
    狀態
    0.07
    😩
    0.07
     isEnabled
    0.07
    Act Density 0.037%

    No Known Activations