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

    Neuronpedia

    INDEX
    Explanations

    flu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .inverse
    -0.06
     poss
    -0.06
     Вели
    -0.06
     Smith
    -0.06
    .orm
    -0.06
    .Normalize
    -0.06
     discs
    -0.06
    iless
    -0.06
    째
    -0.06
    xef
    -0.06
    POSITIVE LOGITS
    flu
    0.09
     Пів
    0.08
    QU
    0.08
     plenty
    0.08
    lut
    0.07
    ")){
↵
    0.07
    ])){↵
    0.07
    .edu
    0.06
     fortune
    0.06
     ули
    0.06
    Act Density 0.001%

    No Known Activations