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

    Neuronpedia

    INDEX
    Explanations

    slow, caching, eat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    1.43
    нда
    1.38
    lı
    1.30
    сть
    1.26
    t
    1.23
    ます
    1.21
    ॅम्प
    1.21
     chuyện
    1.20
    もっと
    1.19
    り
    1.17
    POSITIVE LOGITS
     وعلى
    1.23
    fueled
    1.15
    ัฐ
    1.07
    สรร
    1.07
    Nuevo
    1.05
    bagian
    1.05
     Многие
    1.03
     hundred
    1.02
    ες
    1.02
    ამ
    1.01
    Act Density 0.000%

    No Known Activations