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

    Neuronpedia

    INDEX
    Explanations

    find commands and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‌های
    0.46
    上
    0.45
     compressible
    0.44
     dated
    0.44
     gazed
    0.42
    ্স
    0.41
    δος
    0.41
    ྛ
    0.41
    ెస్
    0.41
    伏
    0.40
    POSITIVE LOGITS
    entu
    0.50
     ツ
    0.50
    nem
    0.47
    inker
    0.47
     إل
    0.47
    him
    0.46
    aina
    0.46
    Means
    0.46
     Tinker
    0.46
     Aus
    0.46
    Act Density 0.001%

    No Known Activations