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

    Neuronpedia

    INDEX
    Explanations

    is/hai/hain/sind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    1.74
    to
    1.69
    deki
    1.61
    ು
    1.56
    ly
    1.48
    schaft
    1.45
    ted
    1.40
    dı
    1.38
    p
    1.36
    s
    1.35
    POSITIVE LOGITS
    الب
    1.62
    ی
    1.53
    ։
    1.50
    ؟
    1.45
    ।
    1.41
    ﻑ
    1.31
    ।।
    1.30
    offsetof
    1.27
    এছাড়া
    1.26
     concaten
    1.25
    Act Density 0.006%

    No Known Activations