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

    Neuronpedia

    INDEX
    Explanations

    code and different languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dresses
    -0.08
    Это
    -0.07
    Addresses
    -0.07
    _MY
    -0.07
    .into
    -0.07
     sektör
    -0.06
    postId
    -0.06
    _FAMILY
    -0.06
    Grow
    -0.06
    niční
    -0.06
    POSITIVE LOGITS
    iller
    0.06
     clever
    0.06
    рат
    0.06
     등
    0.06
    主義
    0.06
    _w
    0.06
    ात
    0.06
     any
    0.06
     поступ
    0.06
    _mutex
    0.06
    Act Density 0.000%

    No Known Activations