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

    Neuronpedia

    INDEX
    Explanations

    combinations and arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     स्तरीय
    0.46
     jir
    0.45
     Settlement
    0.42
     Jihad
    0.42
     Kara
    0.41
    Via
    0.41
     ढूंढ
    0.41
    老婆
    0.41
     Ripple
    0.40
    Selenium
    0.40
    POSITIVE LOGITS
     annunci
    0.49
     marav
    0.47
     poudre
    0.47
     fillets
    0.46
     défin
    0.45
    exhaustive
    0.45
     conformations
    0.45
     deviates
    0.44
     couverts
    0.44
     chiffres
    0.43
    Act Density 0.002%

    No Known Activations