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

    Neuronpedia

    INDEX
    Explanations

    confidence and belief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voluntary
    -0.07
     seja
    -0.06
     сили
    -0.06
     ligne
    -0.06
    方
    -0.06
    emplo
    -0.06
    影响
    -0.06
     priorit
    -0.06
     노출등록
    -0.06
     докум
    -0.06
    POSITIVE LOGITS
    [d
    0.06
     Pred
    0.06
     Tok
    0.06
    shot
    0.06
     brackets
    0.06
    .PL
    0.06
    .JMenuItem
    0.06
    ollectors
    0.06
    Appear
    0.06
    .fake
    0.06
    Act Density 0.029%

    No Known Activations