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

    Neuronpedia

    INDEX
    Explanations

    stars and stellar objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشتقه
    0.52
     അടി
    0.49
     gebruikers
    0.49
    槊
    0.48
    聝
    0.48
     бесплат
    0.47
    0.47
     Акы
    0.47
     getUsersBy
    0.47
     Пользова
    0.46
    POSITIVE LOGITS
     stars
    1.22
     star
    1.12
    star
    0.99
    stars
    0.92
     estrellas
    0.87
     Stars
    0.86
     stellar
    0.86
     звезда
    0.84
    Stars
    0.83
     bintang
    0.81
    Act Density 0.020%

    No Known Activations