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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reign
    -0.09
     braking
    -0.09
     advertising
    -0.08
     brakes
    -0.08
    Advertising
    -0.08
     जिम्म
    -0.08
     constitué
    -0.08
     INA
    -0.08
     trách
    -0.08
     urgently
    -0.08
    POSITIVE LOGITS
    /raw
    0.09
     opción
    0.08
    查询
    0.08
     করলে
    0.08
     반환
    0.08
     옵션
    0.07
    返回
    0.07
    :false
    0.07
     false
    0.07
    0.07
    Act Density 0.008%
    No Known Activations