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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maps
    -0.08
    距离
    -0.07
    imum
    -0.07
     ישראל
    -0.07
    atcher
    -0.07
    锣
    -0.07
    raph
    -0.07
    乙
    -0.07
     continues
    -0.07
     يونيو
    -0.07
    POSITIVE LOGITS
     predecess
    0.07
     FirstName
    0.07
    كثر
    0.07
     defy
    0.06
    特有的
    0.06
    高额
    0.06
    Flying
    0.06
     %@
    0.06
     Percent
    0.06
    Orden
    0.06
    Act Density 0.011%

    No Known Activations