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

    Neuronpedia

    INDEX
    Explanations

    default props

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decolor
    0.51
     produse
    0.47
     sicuramente
    0.46
     Geç
    0.46
     TEXAS
    0.44
    溶液
    0.44
    jač
    0.44
     FLORIDA
    0.43
     продукти
    0.42
     prodotti
    0.42
    POSITIVE LOGITS
     Sailing
    0.44
     sailing
    0.42
     defaults
    0.41
    defaults
    0.41
     abbey
    0.40
    enberg
    0.39
    Defaults
    0.39
     Paw
    0.38
    lodash
    0.38
    Louise
    0.38
    Act Density 0.021%

    No Known Activations