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

    Neuronpedia

    INDEX
    Explanations

    discussing sensitive topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     எட்டு
    0.55
     управ
    0.54
     ۸
    0.49
    ফোঁ
    0.49
     Dolce
    0.48
     tiết
    0.48
     mengatasi
    0.47
     கொண்டு
    0.46
     ८
    0.46
     Năm
    0.46
    POSITIVE LOGITS
    ي
    0.49
    is
    0.45
    oren
    0.45
    可
    0.45
    خان
    0.44
    ものです
    0.44
    adjacency
    0.44
    下面的
    0.43
    örer
    0.43
    kamer
    0.42
    Act Density 0.000%

    No Known Activations