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

    Neuronpedia

    INDEX
    Explanations

    jsfiddle code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    柳
    -0.07
     idx
    -0.06
    Row
    -0.06
     Bentley
    -0.06
    ٨
    -0.06
    ru
    -0.06
    _q
    -0.06
     facet
    -0.06
    avicon
    -0.06
    ился
    -0.06
    POSITIVE LOGITS
    ward
    0.08
     由
    0.07
     posled
    0.07
     mümkün
    0.07
    .Board
    0.07
    udd
    0.07
     Exercises
    0.06
     compromise
    0.06
     کوچک
    0.06
     incon
    0.06
    Act Density 0.003%

    No Known Activations