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

    Neuronpedia

    INDEX
    Explanations

    Assault Hotline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    caps
    0.39
     महज
    0.37
    !`
    0.36
    Ẹ
    0.34
     அழகு
    0.34
    ތ
    0.34
    orithms
    0.33
    allery
    0.33
    𝕜
    0.32
    血糖
    0.32
    POSITIVE LOGITS
     GA
    0.55
     DA
    0.54
     TA
    0.52
     ZA
    0.52
     PA
    0.50
     WA
    0.50
    YA
    0.50
    ΡΑ
    0.48
     GAA
    0.47
    JA
    0.47
    Act Density 0.020%

    No Known Activations