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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towel
    -0.07
    芫
    -0.07
     ____
    -0.07
    ဿ
    -0.07
    妝
    -0.06
    收費
    -0.06
     lần
    -0.06
    ⍢
    -0.06
    🛎
    -0.06
    MASConstraintMaker
    -0.06
    POSITIVE LOGITS
    <tr
    0.08
    .tensor
    0.08
    _series
    0.08
    gal
    0.07
    几家
    0.07
    SizePolicy
    0.07
    accur
    0.07
    ousel
    0.07
    面前
    0.07
    istribution
    0.07
    Act Density 0.001%

    No Known Activations