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

    Neuronpedia

    INDEX
    Explanations

    Swahili words and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PDGF
    0.74
     triggers
    0.70
     ec
    0.70
     Gál
    0.68
     मुकदमा
    0.67
     tern
    0.66
     trigger
    0.65
     före
    0.63
     gall
    0.63
     eroded
    0.62
    POSITIVE LOGITS
    Kwa
    0.85
     kwa
    0.82
     kid
    0.82
     kw
    0.80
    akili
    0.79
     mwen
    0.79
    Bei
    0.78
     ww
    0.78
     hata
    0.78
     kwenye
    0.78
    Act Density 0.041%

    No Known Activations