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

    Neuronpedia

    INDEX
    Explanations

    sign relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ние
    0.41
    ைய
    0.38
     off
    0.36
     spiel
    0.36
     вне
    0.36
    avut
    0.36
     troph
    0.35
     Zeitschr
    0.35
     subst
    0.34
     Weil
    0.34
    POSITIVE LOGITS
    0.54
    没什么
    0.51
    スピード
    0.44
    &$
    0.42
    ∑</
    0.42
     নির্ভরযোগ্য
    0.42
     dirigida
    0.41
    ଚ
    0.40
    र्सेज
    0.40
     liquides
    0.39
    Act Density 0.000%

    No Known Activations