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

    Neuronpedia

    INDEX
    Explanations

    table of contents/summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Từ
    -0.07
    .Fixed
    -0.06
    tx
    -0.06
    імі
    -0.06
     Wikimedia
    -0.06
     понять
    -0.06
    PCP
    -0.06
    евого
    -0.06
    locs
    -0.06
    -0.06
    POSITIVE LOGITS
    moire
    0.07
    $update
    0.07
    /display
    0.06
    <Category
    0.06
     carpet
    0.06
     viv
    0.06
     Giám
    0.06
    Released
    0.06
    ceil
    0.06
    fusc
    0.06
    Act Density 0.001%

    No Known Activations