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
    implify
    -0.07
     prz
    -0.07
     приб
    -0.07
    locals
    -0.07
     kle
    -0.07
    ,options
    -0.07
    -pro
    -0.06
    Word
    -0.06
     çocuk
    -0.06
     champ
    -0.06
    POSITIVE LOGITS
     respectfully
    0.07
    .running
    0.06
    들이
    0.06
     Laura
    0.06
    _wrap
    0.06
    SVG
    0.06
    plemented
    0.06
     Continuous
    0.06
    ponents
    0.06
     dresses
    0.06
    Act Density 0.052%

    No Known Activations