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

    Neuronpedia

    INDEX
    Explanations

    wild

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nonzero
    -0.08
     दब
    -0.07
     bà
    -0.07
    labels
    -0.06
    .subtract
    -0.06
     tf
    -0.06
    <quote
    -0.06
     (),
    -0.06
     decreasing
    -0.06
     exemplo
    -0.06
    POSITIVE LOGITS
     nền
    0.06
    lection
    0.06
    getClientOriginal
    0.06
    ysical
    0.06
     vật
    0.06
     unserer
    0.06
    arth
    0.06
     navig
    0.06
     MOTOR
    0.06
    .getProject
    0.06
    Act Density 0.009%

    No Known Activations