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

    Neuronpedia

    INDEX
    Explanations

    к

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棋牌
    -0.07
    سوب
    -0.07
     якого
    -0.07
    โจ
    -0.07
     أبو
    -0.06
     المش
    -0.06
     bob
    -0.06
     recognised
    -0.06
    �
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    ention
    0.07
    -archive
    0.07
    armac
    0.06
    riage
    0.06
     Nano
    0.06
     truths
    0.06
    <i
    0.06
     средств
    0.06
     Derm
    0.06
     liberation
    0.06
    Act Density 0.000%

    No Known Activations