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

    Neuronpedia

    INDEX
    Explanations

    lists with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Later
    0.42
    Now
    0.41
    fton
    0.41
    Finally
    0.39
     symbiotic
    0.39
    უდ
    0.38
    шон
    0.38
     Recently
    0.38
     scoped
    0.38
     Emiliano
    0.37
    POSITIVE LOGITS
    ammens
    0.40
     Perm
    0.38
    ANTI
    0.37
     ನೆ
    0.36
     mesto
    0.36
     Riga
    0.36
     martes
    0.36
     मंगलवार
    0.35
     Celt
    0.35
     छ
    0.35
    Act Density 0.195%

    No Known Activations