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

    Neuronpedia

    INDEX
    Explanations

    HTTP methods, months, needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     случаях
    1.36
     revoc
    1.28
    łej
    1.25
     cruised
    1.22
     covariate
    1.21
     وهذا
    1.18
    Privacy
    1.16
     whatsoever
    1.14
    AsUp
    1.12
    เรีย
    1.11
    POSITIVE LOGITS
    a
    1.63
    ت
    1.54
    ا
    1.52
    ی
    1.43
    ه
    1.40
    e
    1.39
     fashioned
    1.31
    ে
    1.30
    т
    1.27
    o
    1.27
    Act Density 0.000%

    No Known Activations