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

    Neuronpedia

    INDEX
    Explanations

    sheriff

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vog
    -0.07
     وما
    -0.07
     feeder
    -0.07
     rocker
    -0.07
    Nullable
    -0.07
    Twig
    -0.06
     biking
    -0.06
     metres
    -0.06
     BPM
    -0.06
     vog
    -0.06
    POSITIVE LOGITS
     sheriff
    0.10
     Sheriff
    0.09
     Sher
    0.08
     sher
    0.07
    pard
    0.07
    _other
    0.07
    Sher
    0.07
    くん
    0.07
    Clinton
    0.07
     CHR
    0.07
    Act Density 0.009%

    No Known Activations