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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udd
    -0.07
     fare
    -0.07
    措施
    -0.07
    lette
    -0.07
    otomy
    -0.07
     afdeling
    -0.07
     fizeram
    -0.07
     Levels
    -0.07
    ynamic
    -0.07
    קל
    -0.07
    POSITIVE LOGITS
     காலை
    0.09
    _coords
    0.09
    _coordinates
    0.08
     coef
    0.08
     coordinates
    0.08
     coeff
    0.08
    .coords
    0.08
    coeff
    0.08
     points
    0.08
    coordinates
    0.08
    Act Density 0.035%

    No Known Activations