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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Euler
    -0.07
    ąż
    -0.06
    [hash
    -0.06
     усл
    -0.06
     trai
    -0.06
     blush
    -0.06
     Laugh
    -0.06
    <B
    -0.06
     hug
    -0.06
    .Shapes
    -0.06
    POSITIVE LOGITS
    ्रव
    0.06
     Fleet
    0.06
     fantast
    0.06
    ply
    0.06
    .Ordinal
    0.06
     Rece
    0.06
    อากาศ
    0.06
    ากล
    0.06
    .jd
    0.06
    歯
    0.06
    Act Density 0.008%

    No Known Activations