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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्यक
    -0.07
     Aggregate
    -0.07
    urre
    -0.07
    /logging
    -0.06
     focused
    -0.06
     placed
    -0.06
    โรงเร
    -0.06
    __.
    -0.06
     Boundary
    -0.06
    _fore
    -0.06
    POSITIVE LOGITS
    rej
    0.07
    /mark
    0.06
     Kia
    0.06
    .findAll
    0.06
    -version
    0.06
     Extra
    0.06
     come
    0.06
     rem
    0.06
    meld
    0.06
     uncomfortable
    0.06
    Act Density 0.013%

    No Known Activations