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

    Neuronpedia

    INDEX
    Explanations

    preprocessor macros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    開催
    0.45
     पीएफआई
    0.44
    ।''
    0.42
     छन्
    0.40
    𐰚
    0.39
     पीएचडी
    0.39
     ምር
    0.39
    fitri
    0.39
    曉
    0.39
    💇
    0.39
    POSITIVE LOGITS
    typeof
    0.63
     typeof
    0.59
     macro
    0.58
    宏
    0.58
     macros
    0.57
    ##
    0.55
     Macro
    0.54
    __
    0.52
     ##
    0.52
    macro
    0.51
    Act Density 0.007%

    No Known Activations