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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MACH
    0.28
    ρων
    0.27
    वाट
    0.26
    腹
    0.26
    铺
    0.26
    慈善
    0.25
    рки
    0.25
    委会
    0.25
    ccgi
    0.25
    вшего
    0.25
    POSITIVE LOGITS
    documentclass
    0.54
    textbf
    0.52
    begin
    0.52
    renewcommand
    0.51
    noindent
    0.46
    newcommand
    0.45
    textit
    0.44
    hspace
    0.44
    vspace
    0.43
    includegraphics
    0.41
    Act Density 0.004%

    No Known Activations