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

    Neuronpedia

    INDEX
    Explanations

    conditional code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bilingual
    0.46
     ↑
    0.41
    ‌ని
    0.41
     Supernatural
    0.41
    裸
    0.40
     घे
    0.40
     เนื่องจาก
    0.39
    带有
    0.39
    नों
    0.39
     '#
    0.38
    POSITIVE LOGITS
    mData
    0.52
     ORNL
    0.51
    અમ
    0.50
     Yuk
    0.49
     odors
    0.48
    صور
    0.48
    િન
    0.47
     Ditt
    0.47
    𝓂
    0.47
    m
    0.46
    Act Density 0.000%

    No Known Activations