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

    Neuronpedia

    INDEX
    Explanations

    34

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     druž
    -0.07
     nêu
    -0.06
     Вс
    -0.06
     espacio
    -0.06
     norsk
    -0.06
    wj
    -0.06
    will
    -0.06
    лися
    -0.06
    onces
    -0.06
    uci
    -0.06
    POSITIVE LOGITS
     racket
    0.19
     moll
    0.13
    acket
    0.09
    34
    0.08
    shots
    0.07
    .Dock
    0.07
    allet
    0.07
    ackets
    0.06
     Diana
    0.06
    аторы
    0.06
    Act Density 0.002%

    No Known Activations