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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =zeros
    -0.07
    _producto
    -0.07
     plagiar
    -0.06
    "][$
    -0.06
    izen
    -0.06
     �
    -0.06
    思考
    -0.06
    monds
    -0.06
    SENT
    -0.06
     ה
    -0.06
    POSITIVE LOGITS
    ียด
    0.07
    .volume
    0.07
    rtle
    0.07
     pleasing
    0.06
    .getAttribute
    0.06
     viện
    0.06
    _alive
    0.06
    -wall
    0.06
    ifferent
    0.06
     traffic
    0.06
    Act Density 0.002%

    No Known Activations