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

    Neuronpedia

    INDEX
    Explanations

    Google services and search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    2.09
    ۰
    1.88
    い
    1.87
    ી
    1.83
    م
    1.82
    ه
    1.81
    ü
    1.80
    ó
    1.76
    ты
    1.72
    いる
    1.72
    POSITIVE LOGITS
    an
    1.70
    the
    1.70
    वंश
    1.51
     NDP
    1.50
     Hotspur
    1.48
     Ruhr
    1.47
     odometer
    1.46
     Doodle
    1.45
     AdWords
    1.45
    स
    1.45
    Act Density 0.027%

    No Known Activations