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

    Neuronpedia

    INDEX
    Explanations

    website, forums and urls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Andre
    -0.07
    _PREFIX
    -0.06
     indicating
    -0.06
     Cres
    -0.06
     Peek
    -0.06
    (condition
    -0.06
     asserts
    -0.06
    559
    -0.06
     Ahmed
    -0.06
    -wheel
    -0.05
    POSITIVE LOGITS
    .</
    0.07
    »,
    0.06
    onya
    0.06
     bàn
    0.06
    говор
    0.06
     newPosition
    0.06
     фас
    0.06
     moderation
    0.06
    。</
    0.06
    ?\
    0.06
    Act Density 0.017%

    No Known Activations