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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cascade
    -0.07
    된다
    -0.06
     Peygamber
    -0.06
    되
    -0.06
    .utc
    -0.06
     Spanish
    -0.06
    Focus
    -0.06
     phái
    -0.06
    Mongo
    -0.06
    .DataFrame
    -0.05
    POSITIVE LOGITS
    atti
    0.07
     手
    0.06
     يو
    0.06
     LABEL
    0.06
    ーマ
    0.06
     куст
    0.06
    PHPUnit
    0.06
     brit
    0.06
    TextField
    0.06
     vant
    0.06
    Act Density 0.032%

    No Known Activations