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

    Neuronpedia

    INDEX
    Explanations

    organizer, podcast, skill, palette

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Orrell
    0.44
    otiv
    0.43
    nal
    0.42
    ally
    0.40
    sion
    0.40
     Kelley
    0.39
    vii
    0.38
     practise
    0.38
    शब्द
    0.38
     StandardScaler
    0.38
    POSITIVE LOGITS
     oub
    0.45
     incluindo
    0.45
     supprim
    0.44
     pô
    0.43
     incluyendo
    0.42
    Grou
    0.41
     supprimer
    0.41
     viagem
    0.40
     вверх
    0.40
     custo
    0.39
    Act Density 0.001%

    No Known Activations