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

    Neuronpedia

    INDEX
    Explanations

    Foreign acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     publik
    0.39
    дера
    0.39
     için
    0.39
     üçün
    0.37
    果然
    0.36
    derdag
    0.35
    ;
    0.35
    综
    0.35
     toks
    0.35
    ernet
    0.35
    POSITIVE LOGITS
    ISP
    0.46
    ሰው
    0.41
    upply
    0.41
     വീട്ട
    0.41
    ESP
    0.39
     JSP
    0.39
    USP
    0.39
     breach
    0.39
    jsp
    0.39
     গোটা
    0.39
    Act Density 0.000%

    No Known Activations