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

    Neuronpedia

    INDEX
    Explanations

    following prepositions and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abá
    0.46
    ̣c
    0.43
     availed
    0.42
    ربعة
    0.42
     وجدت
    0.42
    য়োজন
    0.41
    fabs
    0.40
     домо
    0.40
    వేశ
    0.39
     abierto
    0.39
    POSITIVE LOGITS
     (=
    0.43
     더욱
    0.42
    积分
    0.40
    ตอน
    0.40
    IZER
    0.39
     CRUD
    0.39
    越来越
    0.39
     DataFrame
    0.38
     knack
    0.38
     टिश
    0.37
    Act Density 0.006%

    No Known Activations