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

    Neuronpedia

    INDEX
    Explanations

    displaying messages or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Шрифт
    0.44
     шрифт
    0.44
     UIFont
    0.43
     font
    0.42
     Font
    0.42
    字体
    0.39
    Seqlist
    0.38
     maxlength
    0.38
     CreateWindow
    0.38
    Font
    0.37
    POSITIVE LOGITS
     forma
    0.41
    Render
    0.40
     rende
    0.39
    Group
    0.37
     bene
    0.37
     traces
    0.37
    Tracking
    0.37
     render
    0.36
     trac
    0.36
     dissent
    0.36
    Act Density 0.006%

    No Known Activations