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

    Neuronpedia

    INDEX
    Explanations

    Moreover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (&$
    -0.08
    自学
    -0.08
    汇总
    -0.08
     Review
    -0.07
     grids
    -0.07
     Equality
    -0.07
    printed
    -0.06
     dotted
    -0.06
    .AutoField
    -0.06
     revision
    -0.06
    POSITIVE LOGITS
    꼬
    0.07
    的热情
    0.07
     userProfile
    0.07
    ﺳ
    0.07
    ŝ
    0.07
    永遠
    0.07
    /');↵
    0.06
    健康产业
    0.06
     LAND
    0.06
    userData
    0.06
    Act Density 0.013%

    No Known Activations