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

    Neuronpedia

    INDEX
    Explanations

    more or better ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vaak
    0.39
     meist
    0.36
     spesso
    0.35
     perfettamente
    0.34
     stockfoto
    0.34
     často
    0.32
    幾乎
    0.32
     ampia
    0.31
     frequentemente
    0.31
     মূলত
    0.31
    POSITIVE LOGITS
     more
    0.79
    もう少し
    0.72
    もっと
    0.71
     більш
    0.68
     আরও
    0.65
     wäre
    0.64
     더
    0.63
     יותר
    0.63
     lenne
    0.63
    would
    0.62
    Act Density 0.205%

    No Known Activations