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

    Neuronpedia

    INDEX
    Explanations

    line of text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    di
    0.45
     Heterocycl
    0.43
    0.40
    dilate
    0.39
     cls
    0.39
     AIP
    0.39
    दी
    0.38
    ني
    0.38
    די
    0.38
    লাল
    0.38
    POSITIVE LOGITS
     Line
    0.79
     line
    0.76
     newLine
    0.72
     lines
    0.69
    Line
    0.68
     Lines
    0.65
    Lines
    0.64
     الخط
    0.64
    LINE
    0.64
     ライン
    0.63
    Act Density 0.036%

    No Known Activations