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

    Neuronpedia

    INDEX
    Explanations

    indicating comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ല്ലോ
    0.73
    도록
    0.70
     fejleszt
    0.67
     গেলেন
    0.66
    KeepOriginal
    0.65
     পারছেন
    0.65
    ھار
    0.65
    ቦች
    0.64
     겸
    0.64
     memudahkan
    0.63
    POSITIVE LOGITS
     below
    1.35
     above
    1.21
     around
    1.18
     slightly
    1.07
     hovering
    1.05
    below
    1.03
     somewhere
    1.02
     BELOW
    0.99
     flirting
    0.98
     Below
    0.96
    Act Density 0.292%

    No Known Activations