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

    Neuronpedia

    INDEX
    Explanations

    scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ustralia
    -0.06
     Ber
    -0.06
    ernel
    -0.06
    .ext
    -0.06
     надо
    -0.06
    臺灣
    -0.06
     kepada
    -0.06
    .lb
    -0.06
     pus
    -0.06
     Поп
    -0.06
    POSITIVE LOGITS
     depleted
    0.07
    _sv
    0.06
    dirs
    0.06
    593
    0.06
     sentinel
    0.06
    lef
    0.06
    Indices
    0.06
    :n
    0.06
     statistical
    0.06
    Mean
    0.06
    Act Density 0.001%

    No Known Activations