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

    Neuronpedia

    INDEX
    Explanations

    attraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ابق
    -0.06
     πρώτη
    -0.06
     SAND
    -0.06
    ุมภาพ
    -0.06
     zs
    -0.06
     HOL
    -0.06
    атів
    -0.06
    میل
    -0.06
     communist
    -0.06
     Shirley
    -0.06
    POSITIVE LOGITS
     Runtime
    0.07
    (decimal
    0.06
    амет
    0.06
     runtime
    0.06
    swire
    0.06
     Knox
    0.06
    flix
    0.06
    óln
    0.06
    فق
    0.06
     depended
    0.06
    Act Density 0.000%

    No Known Activations