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

    Neuronpedia

    INDEX
    Explanations

    cut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     加
    -0.07
     Updates
    -0.06
     Chat
    -0.06
    (ht
    -0.06
     تک
    -0.06
    ิตภ
    -0.06
     coached
    -0.06
     واست
    -0.06
     Dig
    -0.06
    Дж
    -0.06
    POSITIVE LOGITS
    UnderTest
    0.07
    eterminate
    0.07
     taped
    0.07
     Britt
    0.07
    ındır
    0.07
    .getSource
    0.06
     treadmill
    0.06
     Cruiser
    0.06
     böl
    0.06
    larınızı
    0.06
    Act Density 0.038%

    No Known Activations