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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ň
    -0.08
    嬉
    -0.08
    .GetDirectoryName
    -0.08
    Ň
    -0.07
    赭
    -0.07
    不适
    -0.07
    馁
    -0.07
    喾
    -0.07
    \Extension
    -0.07
     genders
    -0.07
    POSITIVE LOGITS
    .confirm
    0.07
     Lord
    0.07
    Enjoy
    0.07
     channelId
    0.07
    odb
    0.06
    orks
    0.06
    Dom
    0.06
    (params
    0.06
     entre
    0.06
    .rb
    0.06
    Act Density 0.002%

    No Known Activations