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

    Neuronpedia

    INDEX
    Explanations

    yz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    constit
    -0.08
     ادا
    -0.08
    ಿದ್ದ
    -0.07
    SCRIBE
    -0.07
     ه
    -0.07
     منك
    -0.07
    axes
    -0.07
    urrender
    -0.07
    scribe
    -0.07
    Specifications
    -0.07
    POSITIVE LOGITS
     Chau
    0.10
     partnerships
    0.09
     Beziehungen
    0.08
     betr
    0.08
     commas
    0.08
     вза
    0.08
     ürün
    0.08
    /products
    0.08
     ties
    0.07
     products
    0.07
    Act Density 0.013%

    No Known Activations