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

    Neuronpedia

    INDEX
    Explanations

    Rhode

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mans
    -0.08
     bullish
    -0.07
    ้อน
    -0.06
    bm
    -0.06
    animals
    -0.06
     facets
    -0.06
    標準
    -0.06
    reservation
    -0.06
    ewe
    -0.06
     covariance
    -0.06
    POSITIVE LOGITS
     Rhode
    0.12
     chmod
    0.07
     Winnipeg
    0.07
     Notre
    0.07
    راه
    0.07
     ㅇㅇ
    0.07
     کنترل
    0.06
     Providence
    0.06
    getPost
    0.06
     appro
    0.06
    Act Density 0.002%

    No Known Activations