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

    Neuronpedia

    INDEX
    Explanations

    letters and strokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cologne
    0.40
    इं
    0.39
     سنی
    0.38
     stör
    0.37
     ассо
    0.37
    orato
    0.37
    SEO
    0.35
     裏
    0.35
    ொள்
    0.35
    {{
    0.35
    POSITIVE LOGITS
     letter
    0.73
    Letter
    0.70
    letter
    0.69
     Letter
    0.64
     letters
    0.63
    letters
    0.62
     strokes
    0.62
    LETTER
    0.60
    stroke
    0.59
     stroke
    0.58
    Act Density 0.101%

    No Known Activations