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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    精装
    -0.07
     writ
    -0.07
    互动
    -0.07
     latina
    -0.07
    新三
    -0.07
    בדק
    -0.07
     Lumia
    -0.07
     kapı
    -0.07
    建党
    -0.07
     Pride
    -0.06
    POSITIVE LOGITS
     Predict
    0.07
     mL
    0.07
    .spec
    0.07
     gm
    0.07
    只见
    0.07
    :j
    0.06
    极其
    0.06
    pherical
    0.06
    .cross
    0.06
     arrows
    0.06
    Act Density 0.052%

    No Known Activations