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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     सब
    -0.08
     cihaz
    -0.07
     blacks
    -0.07
     Protect
    -0.07
    iedad
    -0.06
     Stop
    -0.06
    Quotes
    -0.06
    壁
    -0.06
    181
    -0.06
    ivar
    -0.06
    POSITIVE LOGITS
    (Component
    0.07
    ября
    0.06
    ồi
    0.06
     justices
    0.06
     наш
    0.06
     schem
    0.06
    .PLL
    0.06
     :|:
    0.06
     fotoğraf
    0.06
     clumsy
    0.06
    Act Density 0.009%

    No Known Activations