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

    Neuronpedia

    INDEX
    Explanations

    list of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     globular
    1.05
     chop
    0.97
     lift
    0.90
    ounce
    0.89
    一体
    0.88
    cted
    0.86
     inertial
    0.84
    ../
    0.84
    averaged
    0.83
    WOOD
    0.83
    POSITIVE LOGITS
    bromide
    1.21
    ів
    1.17
     কাবুল
    1.09
     Bí
    1.09
     bekl
    1.08
    Licenses
    1.07
    اں
    1.05
     Его
    1.04
     Egipto
    1.02
    Bombay
    1.02
    Act Density 0.000%

    No Known Activations