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

    Neuronpedia

    INDEX
    Explanations

    Single digit numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _O
    -0.08
     Athletics
    -0.07
     humanities
    -0.07
     complications
    -0.06
     mitig
    -0.06
    objective
    -0.06
    -
    -0.06
     ід
    -0.06
     speculation
    -0.06
     bitmask
    -0.06
    POSITIVE LOGITS
     yapmış
    0.07
     Enumerator
    0.07
    未
    0.07
    有效
    0.07
    ETY
    0.07
    説明
    0.07
     برگزار
    0.06
    ประสบ
    0.06
    .ReadKey
    0.06
    يز
    0.06
    Act Density 0.023%

    No Known Activations