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

    Neuronpedia

    INDEX
    Explanations

    Computer systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vệ
    -0.07
     Sons
    -0.07
    ,left
    -0.06
    映画
    -0.06
    .export
    -0.06
     bb
    -0.06
    ariant
    -0.06
    kuk
    -0.06
     matriz
    -0.06
    Mix
    -0.06
    POSITIVE LOGITS
    _CONVERT
    0.07
    MARY
    0.06
     Joy
    0.06
     inefficient
    0.06
    ProgressHUD
    0.06
     devise
    0.06
    .elements
    0.06
     شده
    0.06
    .indices
    0.06
     "'.$
    0.06
    Act Density 0.068%

    No Known Activations