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

    Neuronpedia

    INDEX
    Explanations

    precedes disclaimer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.51
    י
    1.51
    𝐲
    1.48
    ی
    1.48
    ㈤
    1.47
    âmara
    1.44
    ේ
    1.41
     personnes
    1.39
    oMatrix
    1.39
     vitesses
    1.39
    POSITIVE LOGITS
    ри
    1.32
     -
    1.31
    ्र
    1.28
    ances
    1.25
     সময়ে
    1.25
    ok
    1.23
    。
    1.22
     ablaze
    1.20
     (
    1.19
    ﻥ
    1.19
    Act Density 0.148%

    No Known Activations