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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inj
    -0.07
     ابزار
    -0.06
     Roller
    -0.06
     aprend
    -0.06
     primitives
    -0.06
    ();↵↵↵↵
    -0.06
     �
    -0.06
     Generate
    -0.06
    w
    -0.06
    '));↵↵
    -0.06
    POSITIVE LOGITS
    ادي
    0.06
    нов
    0.06
    спіль
    0.06
    Berlin
    0.06
     وصل
    0.06
    ουμε
    0.06
     Dunn
    0.06
    .Seek
    0.06
    .height
    0.06
    _scores
    0.06
    Act Density 0.054%

    No Known Activations