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

    Neuronpedia

    INDEX
    Explanations

    wood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     admits
    -0.09
     liked
    -0.08
    _list
    -0.08
    TestCase
    -0.08
    Argument
    -0.07
    <int
    -0.07
    تين
    -0.07
    -0.07
    remove
    -0.07
     administrative
    -0.07
    POSITIVE LOGITS
    鹣
    0.07
    𫮃
    0.07
    judul
    0.07
    mlin
    0.07
    籥
    0.07
     Bbw
    0.07
     Baltic
    0.07
    .Millisecond
    0.07
    avior
    0.07
    玷
    0.07
    Act Density 0.132%

    No Known Activations