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

    Neuronpedia

    INDEX
    Explanations

    publication information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﻦ
    -0.07
    ight
    -0.07
    IGHT
    -0.07
    ニング
    -0.06
    $username
    -0.06
    uras
    -0.06
    IDA
    -0.06
    屋
    -0.06
    -calendar
    -0.06
    uh
    -0.06
    POSITIVE LOGITS
    襻
    0.07
    滗
    0.07
    镚
    0.07
    Ǽ
    0.07
    𬘬
    0.07
     Intelli
    0.07
    荦
    0.06
    0.06
     awesome
    0.06
    >.↵
    0.06
    Act Density 0.019%

    No Known Activations