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

    Neuronpedia

    INDEX
    Explanations

    growth factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divine
    -0.08
     routes
    -0.08
     tử
    -0.08
    住所
    -0.07
    赞
    -0.07
     blaze
    -0.07
     Divine
    -0.07
    inse
    -0.07
    Mutable
    -0.07
    isin
    -0.07
    POSITIVE LOGITS
     građ
    0.08
     BPA
    0.08
     ceremonies
    0.08
     verdriet
    0.08
    0.08
    :param
    0.07
     ceremony
    0.07
     terrem
    0.07
    भीर
    0.07
     raped
    0.07
    Act Density 0.001%

    No Known Activations