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

    Neuronpedia

    INDEX
    Explanations

    mathematics, equations, formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    기는
    0.30
    یت
    0.29
    서는
    0.28
    oughby
    0.27
    会話
    0.26
    ión
    0.26
    ﺶ
    0.25
    hwar
    0.25
    berkeley
    0.25
    ۔
    0.25
    POSITIVE LOGITS
    n
    0.43
    w
    0.41
    r
    0.40
    l
    0.39
    x
    0.38
    ות
    0.33
    j
    0.32
    ’
    0.31
    k
    0.31
     Has
    0.30
    Act Density 1.208%

    No Known Activations