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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nose
    -0.07
     actresses
    -0.07
     excellent
    -0.06
    炖
    -0.06
     Después
    -0.06
     ObjectType
    -0.06
    ед
    -0.06
    quets
    -0.06
     Quando
    -0.06
     dá
    -0.06
    POSITIVE LOGITS
    וץ
    0.07
    اط
    0.07
    .dtd
    0.07
     --------------------------------
    0.07
     UCLA
    0.07
    מנט
    0.06
    室外
    0.06
    요
    0.06
    Advertisements
    0.06
    廿
    0.06
    Act Density 0.022%

    No Known Activations