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

    Neuronpedia

    INDEX
    Explanations

    full, whole, waste, needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     determinato
    0.45
     ønsk
    0.43
     desenvolvimento
    0.42
     tessuto
    0.42
     přek
    0.42
     initially
    0.41
     favorably
    0.41
     respectivos
    0.41
     مشار
    0.41
     poprzez
    0.40
    POSITIVE LOGITS
    HOUSE
    0.47
     জঙ্গ
    0.43
     PUBLIC
    0.42
    крыть
    0.40
     ORGANIZATION
    0.40
    condensation
    0.39
     HOUSE
    0.39
    Match
    0.38
    L
    0.38
    гот
    0.38
    Act Density 0.009%

    No Known Activations