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

    Neuronpedia

    INDEX
    Explanations

    what depends on/best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VRT
    -0.07
     strr
    -0.06
    intr
    -0.06
     ±
    -0.06
     BMI
    -0.06
     ::::::::
    -0.06
    ur
    -0.06
     اق
    -0.06
     Asc
    -0.06
     extraction
    -0.06
    POSITIVE LOGITS
     Nhà
    0.07
     acre
    0.06
    。それ
    0.06
     insignificant
    0.06
    글상위
    0.06
    Invest
    0.06
    碼
    0.06
     categorie
    0.06
     Chevy
    0.06
    침
    0.06
    Act Density 0.049%

    No Known Activations