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

    Neuronpedia

    INDEX
    Explanations

    code, trading, VHDL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.47
     one
    0.45
    ,
    0.42
     was
    0.42
    ?
    0.41
     at
    0.40
     cited
    0.40
    치를
    0.39
     highlights
    0.38
     Highlights
    0.38
    POSITIVE LOGITS
    мести
    0.46
     예약
    0.44
    庻
    0.43
    esercizio
    0.41
     आरोग्य
    0.40
     escuelas
    0.40
     सीड्स
    0.40
    omyosin
    0.39
    ૂત
    0.39
     générations
    0.39
    Act Density 0.000%

    No Known Activations