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

    Neuronpedia

    INDEX
    Explanations

    lists, structures, and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sync
    0.48
     uncertain
    0.45
     mushroom
    0.44
     Bud
    0.44
     trips
    0.44
     grams
    0.44
     gos
    0.44
     bud
    0.43
     autop
    0.42
     usern
    0.42
    POSITIVE LOGITS
    fläche
    0.45
     அடை
    0.45
    Emple
    0.44
    완
    0.44
    LIMIT
    0.43
    Württemberg
    0.43
    Ệ
    0.43
    ی
    0.42
     அனைத்து
    0.42
    λει
    0.42
    Act Density 0.000%

    No Known Activations