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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َب
    -0.07
    殖
    -0.06
     zp
    -0.06
     summed
    -0.06
     représ
    -0.06
     이전
    -0.06
    なかった
    -0.06
     dominated
    -0.05
    ीय
    -0.05
    eses
    -0.05
    POSITIVE LOGITS
     danych
    0.07
    сии
    0.07
    uy
    0.07
    「そう
    0.07
     مک
    0.07
    	LOGGER
    0.07
    .getSimpleName
    0.06
     imprisonment
    0.06
    (mat
    0.06
     PAY
    0.06
    Act Density 0.000%

    No Known Activations