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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     către
    2.19
    𝐀
    2.07
    "/
    1.90
    AL
    1.88
    6
    1.85
    "./
    1.83
    "",
    1.80
    9
    1.80
    ्स
    1.74
     cambiare
    1.73
    POSITIVE LOGITS
    ש
    2.91
    一个
    2.39
    народ
    2.16
    ли
    1.88
     в
    1.85
    ﻲ
    1.78
     couldn
    1.78
    檛
    1.78
     in
    1.76
    ח
    1.75
    Act Density 0.022%

    No Known Activations