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

    Neuronpedia

    INDEX
    Explanations

    start to finish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     давно
    -0.07
    Ten
    -0.07
    认为
    -0.07
    -dialog
    -0.07
    _WRONG
    -0.06
    formik
    -0.06
    ชาต
    -0.06
    ⌒
    -0.06
    にも
    -0.06
    神
    -0.06
    POSITIVE LOGITS
     ltd
    0.07
    摄
    0.07
     삭제
    0.07
    Coverage
    0.06
    onomic
    0.06
    تن
    0.06
     discrepancies
    0.06
    .remove
    0.06
     deleted
    0.06
     Span
    0.06
    Act Density 0.013%

    No Known Activations