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

    Neuronpedia

    INDEX
    Explanations

    Dates and times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     사이
    -0.07
    (builder
    -0.06
    舆论
    -0.06
    scale
    -0.06
     molec
    -0.06
    sales
    -0.06
    ød
    -0.06
     upsetting
    -0.06
     dart
    -0.06
    崤
    -0.06
    POSITIVE LOGITS
     Reyes
    0.07
    项目的
    0.07
    ꪮ
    0.07
     PageInfo
    0.07
    uerdo
    0.07
     Couples
    0.07
     التركي
    0.06
     graded
    0.06
     Ninja
    0.06
    後に
    0.06
    Act Density 0.027%

    No Known Activations