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

    Neuronpedia

    INDEX
    Explanations

    Number formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     слова
    -0.07
     HC
    -0.07
     flexible
    -0.06
    _layer
    -0.06
    orce
    -0.06
     Transfer
    -0.06
    OCR
    -0.06
    背景
    -0.06
    Psych
    -0.06
    RB
    -0.06
    POSITIVE LOGITS
     โดย
    0.08
     Sil
    0.08
     كيل
    0.07
     "%.
    0.06
     MOST
    0.06
    }")
    0.06
    UPDATED
    0.06
     crafting
    0.06
     cul
    0.06
     QtCore
    0.06
    Act Density 0.001%

    No Known Activations