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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _('
    -0.08
    że
    -0.07
    lední
    -0.07
    辦
    -0.07
     yine
    -0.07
     공
    -0.07
    ayd
    -0.06
     gắng
    -0.06
    GPL
    -0.06
    ệ
    -0.06
    POSITIVE LOGITS
     printed
    0.06
     examinations
    0.06
     Chim
    0.06
     Plumbing
    0.06
     nerd
    0.06
    Say
    0.06
     Noise
    0.06
    ,val
    0.06
     pytest
    0.05
     ocup
    0.05
    Act Density 0.004%

    No Known Activations