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

    Neuronpedia

    INDEX
    Explanations

    Zhang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usters
    -0.06
    topl
    -0.06
    080
    -0.06
     sw
    -0.06
     Wave
    -0.06
     se
    -0.06
     perse
    -0.06
     vor
    -0.06
    #Region
    -0.06
    들도
    -0.06
    POSITIVE LOGITS
    .nl
    0.07
    NK
    0.07
     orthodox
    0.07
    頁
    0.07
    纸
    0.07
    ska
    0.07
    .XRLabel
    0.07
    ialias
    0.07
     lesbische
    0.07
     popis
    0.07
    Act Density 0.002%

    No Known Activations