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

    Neuronpedia

    INDEX
    Explanations

    view returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ции
    1.29
    vät
    1.18
    ôt
    1.17
     iyong
    1.16
    ør
    1.13
    ogenetic
    1.13
    அல்ல
    1.13
    вших
    1.13
    ضافة
    1.13
    ви
    1.12
    POSITIVE LOGITS
    d
    1.75
     levar
    1.52
    nsk
    1.47
     sukham
    1.44
     साल
    1.43
    稞
    1.43
    AT
    1.41
    ITTER
    1.38
    스
    1.38
    ﻢ
    1.38
    Act Density 0.000%

    No Known Activations