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

    Neuronpedia

    INDEX
    Explanations

    heroes astray

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nyní
    0.50
     now
    0.44
     nowe
    0.43
    ダル
    0.42
     passports
    0.42
     strategia
    0.42
     линий
    0.41
    now
    0.41
     ormai
    0.41
    ुकी
    0.40
    POSITIVE LOGITS
    mouseout
    0.43
    likely
    0.38
    grass
    0.38
    sequent
    0.38
     Ordnung
    0.38
    废物
    0.38
    දී
    0.38
     رکھنے
    0.38
    ཚ
    0.37
    esters
    0.37
    Act Density 0.002%

    No Known Activations