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

    Neuronpedia

    INDEX
    Explanations

    Ist

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    udes
    0.47
    ude
    0.42
    Se
    0.41
     дей
    0.41
    ಸು
    0.40
    aste
    0.40
    sou
    0.39
    аст
    0.38
     Sex
    0.38
    asey
    0.38
    POSITIVE LOGITS
    elf
    0.45
    ELF
    0.40
    ernum
    0.39
    ेलो
    0.38
    قاف
    0.37
    QueueMutex
    0.36
    يمي
    0.36
     কথাও
    0.36
    llrp
    0.36
     ينا
    0.35
    Act Density 0.000%

    No Known Activations