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

    Neuronpedia

    INDEX
    Explanations

    asking for a better way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ैस
    -0.07
     neg
    -0.07
    ucking
    -0.06
     سع
    -0.06
    先
    -0.06
    Eye
    -0.06
     вважа
    -0.06
     ECS
    -0.06
    不知
    -0.06
     ей
    -0.06
    POSITIVE LOGITS
    ously
    0.07
    annah
    0.06
     ################
    0.06
    -ms
    0.06
     metaData
    0.06
     dựng
    0.06
    оні
    0.06
    ...,
    0.06
    -san
    0.06
    cision
    0.06
    Act Density 0.024%

    No Known Activations