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

    Neuronpedia

    INDEX
    Explanations

    custom-made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @RunWith
    -0.07
    -card
    -0.06
    scroll
    -0.06
    ASSERT
    -0.06
     articulated
    -0.06
    往
    -0.06
    .Tree
    -0.06
    代理
    -0.06
    (work
    -0.06
     Psychological
    -0.06
    POSITIVE LOGITS
     chapel
    0.07
     belief
    0.07
     sauce
    0.07
    _RAW
    0.06
     ＿
    0.06
    玄
    0.06
    703
    0.06
     geil
    0.06
    $L
    0.06
    巻
    0.06
    Act Density 0.058%

    No Known Activations