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

    Neuronpedia

    INDEX
    Explanations

    Greek academic and technical suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hadc
    0.67
    addAlignment
    0.67
    𝖐
    0.62
    ចប់
    0.61
     सीक्व
    0.61
     божомолдор
    0.61
     clockRadius
    0.60
     buddhav
    0.59
     yoj
    0.58
     chromedp
    0.58
    POSITIVE LOGITS
    ν
    1.13
    σ
    1.06
     για
    1.05
     με
    1.05
    μ
    1.05
    η
    1.04
    α
    1.02
     και
    1.02
     από
    1.02
    υ
    1.02
    Act Density 0.002%

    No Known Activations