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

    Neuronpedia

    INDEX
    Explanations

    quantities and ounces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ాన్ని
    1.09
    el
    1.05
    منا
    1.03
    ractions
    0.99
    iqueness
    0.98
    dX
    0.97
    nk
    0.97
    बीएस
    0.95
     Над
    0.95
    raction
    0.94
    POSITIVE LOGITS
    ————————
    0.80
    ╧
    0.77
     pain
    0.74
    awn
    0.72
    ິດຕ
    0.71
     ulo
    0.71
     customizing
    0.71
     जानिए
    0.70
    legg
    0.70
    andoah
    0.68
    Act Density 0.113%

    No Known Activations