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

    Neuronpedia

    INDEX
    Explanations

    fractions and mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.42
    ्या
    1.21
    턴
    1.09
    िकोण
    0.99
    uot
    0.98
    ية
    0.96
    िक्स
    0.92
    cett
    0.92
    ंबित
    0.91
     dane
    0.90
    POSITIVE LOGITS
     (
    0.93
    T
    0.91
    zi
    0.90
    },
    0.87
    ",
    0.87
     प्रातः
    0.86
    тин
    0.85
    alities
    0.84
     in
    0.82
     וי
    0.82
    Act Density 0.062%

    No Known Activations