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

    Neuronpedia

    INDEX
    Explanations

    language, code, identifier, saving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.46
     iniziare
    0.46
    dummies
    0.46
    ˍ
    0.45
     ghee
    0.44
    定義
    0.43
    acrylic
    0.42
     aktivieren
    0.42
     dude
    0.42
    ドキ
    0.41
    POSITIVE LOGITS
    ciąż
    0.45
    slateg
    0.45
    𝖊
    0.45
     setia
    0.44
     जारी
    0.43
     വിദ്യാ
    0.42
     حرب
    0.41
    ๖
    0.41
     stadig
    0.40
     सीख
    0.40
    Act Density 0.005%

    No Known Activations