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

    Neuronpedia

    INDEX
    Explanations

    quart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     หร
    -0.07
     Germans
    -0.07
     эти
    -0.06
     journey
    -0.06
     spam
    -0.06
    _REPO
    -0.06
    şa
    -0.06
    feature
    -0.06
    ｊ
    -0.06
     elements
    -0.06
    POSITIVE LOGITS
     calculator
    0.07
    _RT
    0.07
     tert
    0.06
     tolerate
    0.06
    Saudi
    0.06
     Велик
    0.06
    .python
    0.06
    51
    0.06
    αν
    0.06
     případě
    0.06
    Act Density 0.003%

    No Known Activations