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

    Neuronpedia

    INDEX
    Explanations

    individual liberties and freedom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     starters
    1.24
    💌
    1.19
     Goodreads
    1.17
     schen
    1.14
    TED
    1.13
     webhook
    1.13
    inicio
    1.12
     rearview
    1.12
     sét
    1.10
    ಸೂ
    1.10
    POSITIVE LOGITS
    ة
    1.13
     mulighed
    1.12
     pirm
    1.10
    te
    1.09
    তে
    1.09
    র্ধ্ব
    1.08
    র্য
    1.08
    ए
    1.08
     đủ
    1.07
    ﺓ
    1.07
    Act Density 0.000%

    No Known Activations