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

    Neuronpedia

    INDEX
    Explanations

    balance of X and Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offen
    1.39
    mêmes
    1.38
    ,,,,
    1.30
    lere
    1.30
     ”,
    1.30
     ','
    1.26
    contrar
    1.26
    onnées
    1.25
    ,~
    1.25
    εύ
    1.25
    POSITIVE LOGITS
    ジュエリー
    1.31
    ಇದ
    1.30
    יי
    1.28
    AAC
    1.27
    jats
    1.24
    }.${
    1.24
    )$\
    1.23
    证券
    1.22
     crossorigin
    1.21
    вір
    1.20
    Act Density 0.001%

    No Known Activations