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

    Neuronpedia

    INDEX
    Explanations

    central nervous system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.34
    e
    1.28
    माग
    1.16
    startTimestamp
    1.16
     какую
    1.14
    us
    1.12
    طيني
    1.10
    ورش
    1.09
    u
    1.08
    i
    1.06
    POSITIVE LOGITS
     bounds
    1.11
     statistically
    1.08
     accompany
    1.03
     worm
    1.00
     plump
    1.00
     limp
    0.99
     deforestation
    0.98
    ДИ
    0.98
     considered
    0.97
    itriangular
    0.97
    Act Density 0.003%

    No Known Activations