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

    Neuronpedia

    INDEX
    Explanations

    explaining descriptive details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ዚ
    0.47
    できない
    0.44
     rodzaj
    0.41
     preferentially
    0.41
     Peaks
    0.40
     généralement
    0.39
    ンド
    0.39
    開発
    0.39
     serveur
    0.39
    基本的に
    0.39
    POSITIVE LOGITS
    ko
    0.45
    shape
    0.45
    lük
    0.45
    .\"
    0.43
    lat
    0.43
    .“
    0.42
    golden
    0.41
    Ст
    0.41
    ott
    0.41
    ونکی
    0.40
    Act Density 0.002%

    No Known Activations