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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tended
    -0.07
     corpses
    -0.07
     decoded
    -0.06
    strategy
    -0.06
    alleng
    -0.06
    láda
    -0.06
    ador
    -0.06
     Foundations
    -0.06
     QUE
    -0.06
     Как
    -0.06
    POSITIVE LOGITS
     it
    0.09
     ذلك
    0.07
    ोल
    0.07
    Flags
    0.06
    ��
    0.06
    را
    0.06
    'It
    0.06
    .|
    0.06
     �
    0.06
    _dot
    0.06
    Act Density 0.041%

    No Known Activations