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

    Neuronpedia

    INDEX
    Explanations

    url

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SOCK
    -0.07
    ator
    -0.07
     irrespective
    -0.07
    oins
    -0.06
    夏
    -0.06
    ators
    -0.06
     esposa
    -0.06
    ale
    -0.06
     beste
    -0.06
     İmparator
    -0.06
    POSITIVE LOGITS
     regained
    0.07
     пит
    0.07
     dryer
    0.06
     inspir
    0.06
     нап
    0.06
    objectId
    0.06
     bmi
    0.06
     irc
    0.06
    初始化
    0.06
     tand
    0.06
    Act Density 0.017%

    No Known Activations