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

    Neuronpedia

    INDEX
    Explanations

    python function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    **
    0.66
     ним
    0.62
    (**
    0.60
     مط
    0.60
    ([]
    0.59
     me
    0.59
     мной
    0.58
    ()*
    0.58
    0.58
    [:]
    0.56
    POSITIVE LOGITS
    def
    1.63
     Def
    1.17
     DEFIN
    1.13
    Def
    1.12
     def
    1.10
     DEF
    1.09
     Defin
    1.08
    DEF
    0.99
    class
    0.88
     defini
    0.86
    Act Density 0.153%

    No Known Activations