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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opción
    -0.07
    -ass
    -0.07
     phiếu
    -0.07
     wcs
    -0.07
    िलत
    -0.07
     ();↵
    -0.07
     interiors
    -0.06
    ριν
    -0.06
    onical
    -0.06
    opot
    -0.06
    POSITIVE LOGITS
     mum
    0.07
    港
    0.06
     borderRadius
    0.06
     primaryKey
    0.06
     forefront
    0.06
     femmes
    0.06
     besoin
    0.06
     Bộ
    0.06
     мик
    0.06
     law
    0.06
    Act Density 0.001%

    No Known Activations