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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    556
    -0.08
    157
    -0.07
    ٫
    -0.07
     polishing
    -0.06
    158
    -0.06
    559
    -0.06
    xn
    -0.06
    amenti
    -0.06
    yg
    -0.06
    ObjectOfType
    -0.06
    POSITIVE LOGITS
    aid
    0.07
    .Public
    0.06
    _extract
    0.06
     oldest
    0.06
     giai
    0.06
    -load
    0.06
     Pols
    0.06
     sak
    0.06
     کاربران
    0.06
     JLabel
    0.06
    Act Density 0.230%

    No Known Activations