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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :::::::
    -0.06
    ETY
    -0.06
    주시
    -0.06
    --
    -0.06
     존
    -0.06
    ～
    -0.06
    ζη
    -0.06
     Це
    -0.05
    žený
    -0.05
    meniz
    -0.05
    POSITIVE LOGITS
    MX
    0.07
    lacağ
    0.07
    会议
    0.07
     Х
    0.07
     BufferedImage
    0.07
    MYSQL
    0.06
    Unary
    0.06
     Eb
    0.06
    _WORK
    0.06
     Antworten
    0.06
    Act Density 0.034%

    No Known Activations