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

    Neuronpedia

    INDEX
    Explanations

    object and its derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    1.50
     і
    1.28
     been
    1.27
     می
    1.22
     а
    1.20
     یا
    1.19
     な
    1.18
     to
    1.15
    textured
    1.13
     کنید
    1.12
    POSITIVE LOGITS
    t
    1.60
    p
    1.56
    i
    1.41
    n
    1.37
     Object
    1.30
    ী
    1.27
    m
    1.25
     object
    1.22
    ர்
    1.02
    object
    1.00
    Act Density 0.075%

    No Known Activations