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

    Neuronpedia

    INDEX
    Explanations

    penalty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reference
    -0.07
    _release
    -0.06
    sys
    -0.06
     undercut
    -0.06
    _Delay
    -0.06
    عکس
    -0.06
    -up
    -0.06
    celain
    -0.06
     urlencode
    -0.06
     eggs
    -0.06
    POSITIVE LOGITS
     Hague
    0.11
     Boca
    0.09
     penalty
    0.08
    _row
    0.07
    يك
    0.07
     Mia
    0.06
     pending
    0.06
     ROW
    0.06
     guarantees
    0.06
     Luk
    0.06
    Act Density 0.002%

    No Known Activations