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

    Neuronpedia

    INDEX
    Explanations

    Reviews and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    검
    -0.08
     vont
    -0.07
     observers
    -0.07
    gl
    -0.07
     sanar
    -0.07
    yiş
    -0.07
     cannabinoids
    -0.07
    titel
    -0.07
     CASH
    -0.07
    ీల
    -0.07
    POSITIVE LOGITS
    看看
    0.09
     внимательно
    0.09
    なら
    0.08
     enjoy
    0.08
     someday
    0.08
     enjoying
    0.08
     ianao
    0.08
    ぜひ
    0.08
    -Regular
    0.08
    了解
    0.08
    Act Density 0.227%

    No Known Activations