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

    Neuronpedia

    INDEX
    Explanations

    result of collected data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лой
    0.52
    лес
    0.45
     B
    0.42
    B
    0.38
    лое
    0.37
    ґ
    0.35
    лым
    0.35
    X
    0.35
     Bernhard
    0.35
    ALTERNATIVNAMEN
    0.35
    POSITIVE LOGITS
     facere
    0.44
     ///<
    0.42
    상품
    0.41
     проводится
    0.40
     reserves
    0.40
    klik
    0.39
     සෑම
    0.39
     cliquer
    0.39
     semblable
    0.39
     prevención
    0.38
    Act Density 0.000%

    No Known Activations