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

    Neuronpedia

    INDEX
    Explanations

    various topics with advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     że
    -0.08
    Präs
    -0.08
     бы
    -0.08
     accelerating
    -0.08
    决定了
    -0.08
     Gefühl
    -0.07
     bodies
    -0.07
     cosmetic
    -0.07
    ões
    -0.07
     لماذا
    -0.07
    POSITIVE LOGITS
    �
    0.08
    hay
    0.08
     ange
    0.07
     view
    0.07
     along
    0.07
    loom
    0.07
    奇纳
    0.07
     Thứ
    0.06
    uffix
    0.06
    を中心に
    0.06
    Act Density 0.115%

    No Known Activations