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

    Neuronpedia

    INDEX
    Explanations

    LaTeX package inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nawet
    0.38
     Inequality
    0.37
    䧼
    0.35
    Quote
    0.34
     அடித்த
    0.34
     навіть
    0.33
     Fudge
    0.33
     cracks
    0.33
    这是一个
    0.33
     Crack
    0.33
    POSITIVE LOGITS
    ᅪ
    0.43
    വിൽ
    0.39
    ediaan
    0.37
    ଟି
    0.37
    taxi
    0.36
    șa
    0.36
    gaxModule
    0.36
     ادي
    0.36
     hydroxyl
    0.35
     اجرا
    0.35
    Act Density 0.008%

    No Known Activations