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

    Neuronpedia

    INDEX
    Explanations

    compiling lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     создании
    0.46
    または
    0.42
     또는
    0.42
     অথবা
    0.41
     அதனால்
    0.41
     하여
    0.41
     અથવા
    0.40
    的大
    0.40
    ﻐ
    0.39
     முற்ற
    0.39
    POSITIVE LOGITS
    вается
    0.47
    monia
    0.46
    1
    0.46
    3
    0.45
    ئة
    0.45
    us
    0.45
    o
    0.45
    ты
    0.44
    fea
    0.43
    5
    0.43
    Act Density 0.069%

    No Known Activations