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

    Neuronpedia

    INDEX
    Explanations

    studying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Medium
    -0.07
     pitchers
    -0.07
     delegate
    -0.06
     ו
    -0.06
     entirety
    -0.06
     vanish
    -0.06
    _active
    -0.06
     purchasers
    -0.06
    丰富多彩
    -0.06
     justices
    -0.06
    POSITIVE LOGITS
    #error
    0.08
    FUNC
    0.07
    'a
    0.07
     بعيد
    0.07
     LA
    0.07
    回落
    0.07
    xAC
    0.07
    熟悉
    0.06
    ORDER
    0.06
    (Process
    0.06
    Act Density 0.097%

    No Known Activations