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

    Neuronpedia

    INDEX
    Explanations

    string, sys, len, random

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    行った
    0.52
    וג
    0.51
    GID
    0.51
    HARAD
    0.49
    ARTI
    0.49
    лади
    0.47
    েলে
    0.46
    тке
    0.46
    ﻏ
    0.46
    רק
    0.45
    POSITIVE LOGITS
    len
    0.51
     점
    0.47
     aç
    0.46
     civilization
    0.45
     end
    0.45
     शु
    0.43
     میں
    0.42
     seal
    0.42
     spend
    0.42
     ity
    0.41
    Act Density 0.001%

    No Known Activations