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

    Neuronpedia

    INDEX
    Explanations

    probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    但
    -0.07
    .addTab
    -0.07
    ところ
    -0.07
     mannen
    -0.07
    (test
    -0.06
     boxes
    -0.06
    ถาม
    -0.06
    ी-
    -0.06
    _emb
    -0.06
    DOMContentLoaded
    -0.06
    POSITIVE LOGITS
    amage
    0.07
     USC
    0.06
    सम
    0.06
     utilization
    0.06
     Jason
    0.06
    ัศ
    0.06
    �
    0.06
    ych
    0.06
    ество
    0.06
    Song
    0.06
    Act Density 0.042%

    No Known Activations