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

    Neuronpedia

    INDEX
    Explanations

    say the ending -tics/-etics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    儀
    -0.07
     нового
    -0.07
     tractor
    -0.06
     tématu
    -0.06
    New
    -0.06
    itting
    -0.06
    yyyyMMdd
    -0.06
     tvá
    -0.06
    аря
    -0.06
     Tucker
    -0.06
    POSITIVE LOGITS
    -res
    0.06
    ORAGE
    0.06
    gies
    0.06
     Senator
    0.06
    лед
    0.06
     comparison
    0.06
    cam
    0.06
     analogy
    0.06
    Ћ
    0.06
    '>↵↵
    0.05
    Act Density 0.029%

    No Known Activations