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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     downloads
    -0.07
    ults
    -0.07
     Left
    -0.06
    THE
    -0.06
     Back
    -0.06
     BACK
    -0.06
    pw
    -0.06
     тем
    -0.06
    &C
    -0.06
     कम
    -0.06
    POSITIVE LOGITS
     devise
    0.07
     staining
    0.06
     γ
    0.06
     lasc
    0.06
    γ
    0.06
    voir
    0.06
     Γ
    0.06
    USAGE
    0.06
     ustanov
    0.06
    .Syntax
    0.06
    Act Density 0.055%

    No Known Activations