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

    Neuronpedia

    INDEX
    Explanations

    XML UI orientations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    苘
    -0.08
    (left
    -0.08
     QPoint
    -0.07
    טכנ
    -0.07
    .elapsed
    -0.07
     élè
    -0.07
     ContentView
    -0.07
     vect
    -0.07
    升温
    -0.07
     MatTable
    -0.07
    POSITIVE LOGITS
    yan
    0.08
     TB
    0.08
    lr
    0.07
    .alibaba
    0.07
    Ba
    0.07
     pus
    0.07
     rb
    0.07
    所有
    0.07
    andra
    0.07
     nas
    0.07
    Act Density 0.002%

    No Known Activations