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

    Neuronpedia

    INDEX
    Explanations

    credit and debit explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    2.14
    માં
    1.96
    Привет
    1.87
    ي
    1.81
    ق
    1.75
    ﻕ
    1.73
    ols
    1.70
    ord
    1.68
    ok
    1.64
    lad
    1.63
    POSITIVE LOGITS
    ک
    2.31
     suatu
    2.03
    ifiably
    2.03
    𝓱
    1.82
     وعلى
    1.80
     эту
    1.79
    по
    1.76
     таки
    1.73
    า
    1.72
     mayoría
    1.70
    Act Density 0.018%

    No Known Activations