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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     İslâm
    -0.07
     credits
    -0.06
    林
    -0.06
     Retirement
    -0.06
     토
    -0.06
    dbl
    -0.06
    Directory
    -0.06
     Trib
    -0.06
    Cos
    -0.06
     Showcase
    -0.06
    POSITIVE LOGITS
     PLEASE
    0.07
     assort
    0.06
     undefined
    0.06
    iculture
    0.06
    bounce
    0.06
     imply
    0.06
     evenings
    0.06
     Generating
    0.06
     اسم
    0.06
    ıt
    0.06
    Act Density 0.012%

    No Known Activations