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

    Neuronpedia

    INDEX
    Explanations

    Chinese speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probabilities
    -0.10
    _prob
    -0.09
    Prob
    -0.09
     probabil
    -0.08
     Prob
    -0.08
     algorithm
    -0.08
     vali
    -0.08
    _algorithm
    -0.08
     probs
    -0.08
    .vec
    -0.08
    POSITIVE LOGITS
    telephone
    0.10
     booming
    0.10
    声音
    0.09
    idle
    0.09
     telephone
    0.09
     ಮಾತನಾಡ
    0.09
    Telephone
    0.09
    female
    0.09
    讲话
    0.09
     recordings
    0.09
    Act Density 0.003%

    No Known Activations