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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     داخلی
    -0.07
    ;


↵
    -0.06
     přísluš
    -0.06
     رنگ
    -0.06
    ağa
    -0.06
     کاربر
    -0.06
    _normals
    -0.06
    dál
    -0.06
     مرکزی
    -0.06
     داشته
    -0.06
    POSITIVE LOGITS
        ↵    ↵    ↵    ↵
    0.07
    !*
    0.07
     Tup
    0.07
    ΙΟΥ
    0.07
     UserModel
    0.07
    ursion
    0.07
    ा↵↵
    0.06
     nineteen
    0.06
     AIR
    0.06
    .Imp
    0.06
    Act Density 0.000%

    No Known Activations