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

    Neuronpedia

    INDEX
    Explanations

    time and repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eniz
    -0.06
    Td
    -0.06
     ample
    -0.06
    _booking
    -0.06
    orderby
    -0.06
    OULD
    -0.06
     Ish
    -0.06
    Err
    -0.06
     Provides
    -0.06
     vej
    -0.06
    POSITIVE LOGITS
     влия
    0.07
    /www
    0.06
     shrugged
    0.06
    дром
    0.06
    316
    0.06
     chemicals
    0.06
    _transfer
    0.06
    环境
    0.06
    .NaN
    0.06
    ";
    0.06
    Act Density 0.033%

    No Known Activations