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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stitching
    -0.09
     Tribute
    -0.08
     baking
    -0.08
     quantidade
    -0.08
     viên
    -0.07
     crawling
    -0.07
     stitched
    -0.07
    ophobia
    -0.07
    Kick
    -0.07
     dobu
    -0.07
    POSITIVE LOGITS
     Faust
    0.09
     редко
    0.09
     bist
    0.09
     변
    0.09
     duplex
    0.08
     IOError
    0.08
     io
    0.08
    cycling
    0.08
    PAIR
    0.08
     परिवर्तन
    0.08
    Act Density 0.005%

    No Known Activations