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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .LastName
    -0.08
     pooling
    -0.08
    .hover
    -0.07
     vệ
    -0.07
    :ss
    -0.07
    无论如何
    -0.07
    ivot
    -0.07
     MMA
    -0.07
    日内
    -0.07
    (preg
    -0.07
    POSITIVE LOGITS
    ่าย
    0.07
    谄
    0.07
     setType
    0.07
    𐌺
    0.07
    셒
    0.06
    וצר
    0.06
    忍
    0.06
    ראל
    0.06
    יצע
    0.06
    諮詢
    0.06
    Act Density 0.001%

    No Known Activations