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

    Neuronpedia

    INDEX
    Explanations

    Alexa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тся
    1.43
    ির
    1.38
    sust
    1.38
    su
    1.31
    ፈጥ
    1.30
    며
    1.30
    atas
    1.30
    sm
    1.29
    solved
    1.28
    ্র
    1.27
    POSITIVE LOGITS
    ا
    1.50
    い
    1.49
    くちゃ
    1.48
     okra
    1.40
    i
    1.37
    ক্ট
    1.30
    ی
    1.27
    ج
    1.27
    롭
    1.24
    ะ
    1.23
    Act Density 0.005%

    No Known Activations