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

    Neuronpedia

    INDEX
    Explanations

    examples and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ford
    0.46
    टर
    0.46
    Yellow
    0.43
    ↵
    0.41
    লে
    0.41
    le
    0.40
    let
    0.40
    YC
    0.40
    ley
    0.39
    Or
    0.39
    POSITIVE LOGITS
     aliquot
    0.54
     plufieurs
    0.49
     има
    0.49
     roca
    0.48
     ಉತ್ತರ
    0.47
     تربيع
    0.47
     Zugriff
    0.47
     సాహిత్య
    0.47
     inode
    0.45
     fak
    0.45
    Act Density 0.002%

    No Known Activations