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

    Neuronpedia

    INDEX
    Explanations

    Lightness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riters
    -0.09
    werp
    -0.08
    /local
    -0.08
     jornadas
    -0.08
    Jacob
    -0.07
    _versions
    -0.07
     ouvrage
    -0.07
     varargin
    -0.07
    args
    -0.07
     transpose
    -0.07
    POSITIVE LOGITS
     bip
    0.08
     vrucht
    0.08
    ‌کن
    0.08
     pentru
    0.07
    0.07
    قان
    0.07
     optim
    0.07
     fi
    0.07
     fertile
    0.07
     miele
    0.07
    Act Density 0.001%
    No Known Activations