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

    Neuronpedia

    INDEX
    Explanations

    answer label after "is"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }{-
    0.38
    ("/",
    0.38
     تكبرها
    0.38
     неуда
    0.38
    UnitTest
    0.37
     failings
    0.37
    ድግዳ
    0.37
    Assignments
    0.36
     கன
    0.36
    inguistic
    0.36
    POSITIVE LOGITS
     C
    0.39
     underwent
    0.39
     B
    0.39
     b
    0.38
     Mostly
    0.38
     Visiting
    0.38
     A
    0.38
     yes
    0.37
     Ꭰ
    0.36
    Historical
    0.36
    Act Density 0.032%

    No Known Activations