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

    Neuronpedia

    INDEX
    Explanations

    command/ranks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /per
    -0.06
    deep
    -0.06
    �
    -0.06
    阵
    -0.06
    ेप
    -0.06
    iset
    -0.06
     kolay
    -0.06
    ами
    -0.06
    asyonu
    -0.06
    方案
    -0.06
    POSITIVE LOGITS
     subordinate
    0.07
     seniors
    0.07
    ToFile
    0.07
    ordinates
    0.07
    fabs
    0.07
    anked
    0.06
     eleştir
    0.06
     @"\
    0.06
    CDF
    0.06
    _capability
    0.06
    Act Density 0.230%

    No Known Activations