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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nas
    -0.07
    -med
    -0.07
    _bill
    -0.06
    ンス
    -0.06
     median
    -0.06
    ikhail
    -0.06
    Pa
    -0.06
     ATTRIBUTE
    -0.05
    ��
    -0.05
    тон
    -0.05
    POSITIVE LOGITS
    oli
    0.07
    :bg
    0.07
     Allowed
    0.07
     lidé
    0.07
     奥
    0.07
    Instagram
    0.06
    .setRotation
    0.06
    息
    0.06
    requested
    0.06
     certifications
    0.06
    Act Density 0.000%

    No Known Activations