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

    Neuronpedia

    INDEX
    Explanations

    so that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    od
    0.35
    ra
    0.34
    ena
    0.33
     A
    0.33
     R
    0.32
    ant
    0.30
     bilingual
    0.30
    س
    0.30
     passo
    0.29
    '";
    0.29
    POSITIVE LOGITS
    ේ
    0.29
    는데
    0.28
    тов
    0.26
    тами
    0.26
    щения
    0.25
    ﻂ
    0.25
    shells
    0.25
    ке
    0.24
    к
    0.24
    ют
    0.24
    Act Density 0.042%

    No Known Activations