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

    Neuronpedia

    INDEX
    Explanations

    defining purposes or following definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     แพ
    0.50
     মাসিক
    0.49
     লাগ
    0.48
     લઇ
    0.47
     ډاونلوډ
    0.45
    legate
    0.44
     ދ
    0.43
     festiv
    0.43
    ﺔ
    0.43
     ລັບ
    0.43
    POSITIVE LOGITS
    T
    0.49
    BackColor
    0.46
    s
    0.46
    स्वर
    0.43
     qr
    0.43
    τρα
    0.43
    sl
    0.42
    고
    0.41
     portuguesa
    0.41
    sb
    0.41
    Act Density 0.001%

    No Known Activations