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

    Neuronpedia

    INDEX
    Explanations

    calculations and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    app
    0.55
    Р
    0.48
    ю
    0.46
    গ
    0.43
    Б
    0.42
     rupee
    0.42
    ي
    0.42
    يق
    0.41
    ).
    0.41
    வ
    0.39
    POSITIVE LOGITS
     nejen
    0.50
     parsing
    0.49
    ynyt
    0.43
     meiosis
    0.42
     ओनली
    0.41
     περισσότε
    0.39
    Parsing
    0.39
     χώ
    0.38
     oltre
    0.37
     cris
    0.37
    Act Density 0.000%

    No Known Activations