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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     davran
    -0.09
    aniem
    -0.07
     применения
    -0.07
     bulun
    -0.07
    ﰌ
    -0.07
    랖
    -0.06
    ⛑
    -0.06
     do
    -0.06
    רז
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    Emoji
    0.08
     Vul
    0.07
     materially
    0.07
    _portfolio
    0.06
     Profit
    0.06
    UNDER
    0.06
    affiliate
    0.06
     Manafort
    0.06
    orough
    0.06
    ).__
    0.06
    Act Density 0.099%

    No Known Activations