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

    Neuronpedia

    INDEX
    Explanations

    speaking, members, promotions, decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     btw
    1.68
     Aktual
    1.58
    ᴊ
    1.52
     Funktions
    1.50
    allar
    1.46
    Referencias
    1.45
    मु
    1.44
    gggg
    1.41
    Ин
    1.39
     Aktien
    1.35
    POSITIVE LOGITS
    ా
    1.22
    دة
    1.13
    ো
    1.11
    চনা
    1.06
     люби
    1.03
    у
    1.02
     dioxide
    1.01
     favourite
    1.01
     rank
    1.00
    €™
    1.00
    Act Density 0.000%

    No Known Activations