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

    Neuronpedia

    INDEX
    Explanations

    Complex sentence structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nal
    -0.07
    ریک
    -0.07
     initialised
    -0.07
     STYLE
    -0.06
     cush
    -0.06
     mnist
    -0.06
    ках
    -0.06
     Fo
    -0.06
    (pro
    -0.06
     comida
    -0.06
    POSITIVE LOGITS
    สนาม
    0.09
    Gift
    0.07
    .ibm
    0.07
     SEM
    0.07
     Dates
    0.06
     pieces
    0.06
    .Helpers
    0.06
     While
    0.06
     سنگ
    0.06
    ugins
    0.06
    Act Density 0.000%

    No Known Activations