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

    Neuronpedia

    INDEX
    Explanations

    bulge outward, test multiple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vény
    0.56
    yl
    0.50
     اكتب
    0.49
    vita
    0.49
    lettes
    0.49
    uleiro
    0.48
    啉
    0.48
    azze
    0.48
    vm
    0.47
    letion
    0.47
    POSITIVE LOGITS
    ід
    0.52
     шири
    0.48
    Ꮲ
    0.47
     цвет
    0.46
     coroner
    0.44
    ина
    0.44
     genetic
    0.44
    ังก
    0.43
     экс
    0.43
    Assim
    0.43
    Act Density 0.000%

    No Known Activations