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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ishops
    -0.07
    -n
    -0.07
    ropy
    -0.06
     spinning
    -0.06
     neur
    -0.06
    summary
    -0.06
    .getWidth
    -0.06
    sqrt
    -0.06
     locom
    -0.06
    Wr
    -0.06
    POSITIVE LOGITS
    ाजस
    0.07
     Official
    0.07
     جديد
    0.07
    άννης
    0.06
    _cid
    0.06
     (...)
    0.06
     Confirm
    0.06
    _BUS
    0.06
    Confirm
    0.06
    صات
    0.06
    Act Density 0.029%

    No Known Activations