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

    Neuronpedia

    INDEX
    Explanations

    current frontrunner champion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mimics
    0.87
    ,
    0.80
    x
    0.71
    load
    0.70
     مصنوع
    0.70
     made
    0.68
    गी
    0.67
    scale
    0.67
    పే
    0.66
     imag
    0.66
    POSITIVE LOGITS
     OpenGL
    1.10
     Men
    1.09
    Ｏ
    1.05
    EXPERIMENTAL
    1.05
     Establishing
    1.04
     Edmund
    1.04
     Deformation
    1.03
     Conference
    1.02
    教师
    1.00
     Protest
    1.00
    Act Density 0.000%

    No Known Activations