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

    Neuronpedia

    INDEX
    Explanations

    section/option/module 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tỏa
    0.52
     управ
    0.50
     tiết
    0.49
    ফোঁ
    0.49
     எட்டு
    0.49
     optimally
    0.48
     optimise
    0.48
     Năm
    0.47
     Agustus
    0.47
     mengatasi
    0.46
    POSITIVE LOGITS
    ي
    0.52
    下面的
    0.45
    速度
    0.44
    örer
    0.43
    shooter
    0.43
    خان
    0.42
     muž
    0.42
    可
    0.42
    kamer
    0.40
    ი
    0.40
    Act Density 0.011%

    No Known Activations