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

    Neuronpedia

    INDEX
    Explanations

    specific markers like asterisks or periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wq
    0.39
    ρον
    0.38
    שי
    0.38
    πε
    0.38
    র্ম
    0.36
    кина
    0.36
    wxT
    0.36
    υτό
    0.36
    CacheV
    0.36
    ᓄ
    0.36
    POSITIVE LOGITS
     причем
    0.52
     Interestingly
    0.41
     มี
    0.39
     Bapak
    0.39
     Lö
    0.38
     Citadel
    0.38
     Président
    0.38
    note
    0.38
     Confront
    0.38
     (!)
    0.38
    Act Density 0.161%

    No Known Activations