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

    Neuronpedia

    INDEX
    Explanations

    in spite of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ذة
    0.40
    صرية
    0.39
     त्रि
    0.38
     heads
    0.38
    ullie
    0.37
     Heads
    0.37
     ছোট্ট
    0.37
    getMeteringAreas
    0.37
    珈
    0.37
    ربية
    0.37
    POSITIVE LOGITS
     spite
    0.57
    fulness
    0.45
     spleen
    0.45
    ful
    0.42
    MAC
    0.41
    FUL
    0.39
    ner
    0.39
     ולא
    0.39
    flower
    0.38
     Spit
    0.38
    Act Density 0.000%

    No Known Activations