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

    Neuronpedia

    INDEX
    Explanations

    Keywords and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     medan
    0.48
     dast
    0.46
     oferta
    0.45
     przed
    0.44
     ज़
    0.43
     aquesta
    0.43
     oleks
    0.43
     kand
    0.43
     costes
    0.42
     desta
    0.42
    POSITIVE LOGITS
    </u>
    0.45
    ,
    0.42
    </h2>
    0.41
    ize
    0.40
     counseling
    0.40
     /ˈ
    0.40
     corretamente
    0.39
     फसलों
    0.38
     Vineyard
    0.38
    ajou
    0.38
    Act Density 0.000%

    No Known Activations