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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haired
    -0.07
     任
    -0.07
     ích
    -0.07
    收益
    -0.06
    ');?>"
    -0.06
    ､
    -0.06
     英
    -0.06
    .WebElement
    -0.06
    ====↵
    -0.06
    شركة
    -0.06
    POSITIVE LOGITS
    Busy
    0.07
    bubble
    0.07
    .back
    0.06
    key
    0.06
     bubble
    0.06
     bubbles
    0.06
    려
    0.06
    .wav
    0.06
    Way
    0.06
     tolerated
    0.06
    Act Density 0.000%

    No Known Activations