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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Random
    -0.07
    FPS
    -0.06
     živ
    -0.06
    CUS
    -0.06
     марта
    -0.06
     vur
    -0.06
     ряд
    -0.06
    一点
    -0.06
     pedigree
    -0.06
    Hola
    -0.06
    POSITIVE LOGITS
     Bảo
    0.07
     Enlight
    0.07
     flawless
    0.06
     tuo
    0.06
    landı
    0.06
    ’:
    0.06
    .semantic
    0.06
     literally
    0.06
    abet
    0.06
    ~-
    0.06
    Act Density 0.000%

    No Known Activations