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

    Neuronpedia

    INDEX
    Explanations

    code and structured contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ాము
    0.43
     ৪৯
    0.41
    piele
    0.41
    ステージ
    0.39
     기간
    0.39
    |.|
    0.38
    ाइए
    0.37
    伎
    0.37
     двох
    0.36
     Canon
    0.35
    POSITIVE LOGITS
    whitespace
    0.42
     fréqu
    0.40
    鰯
    0.38
    陖
    0.37
    苇
    0.37
    produkt
    0.37
     complemento
    0.36
     fractions
    0.35
    Rq
    0.35
     excès
    0.34
    Act Density 0.000%

    No Known Activations