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

    Neuronpedia

    INDEX
    Explanations

    work. instruments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DCHECK
    0.71
     विवेकान
    0.71
     หัว
    0.70
     computerScore
    0.67
     Strah
    0.66
     دیکھا
    0.65
    廈
    0.64
    ObjectHideFlags
    0.63
    澀
    0.63
     flavonoids
    0.63
    POSITIVE LOGITS
    作用
    0.69
     groups
    0.68
     গোষ্ঠ
    0.65
    而出
    0.64
     instruments
    0.64
     predecessors
    0.63
     spn
    0.62
    amel
    0.62
     চূড়ান্ত
    0.62
     ظهر
    0.62
    Act Density 0.000%

    No Known Activations