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

    Neuronpedia

    INDEX
    Explanations

    films

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    染
    -0.07
    .Mvc
    -0.07
     eylem
    -0.06
    ()],
    -0.06
    departureday
    -0.06
    имости
    -0.06
    'D
    -0.06
    'S
    -0.06
     treff
    -0.06
    '})↵↵
    -0.06
    POSITIVE LOGITS
     Bol
    0.06
     Nga
    0.06
     Abby
    0.06
     강
    0.06
    ----</
    0.06
    락
    0.06
    af
    0.06
     Magick
    0.06
     ощ
    0.06
    маг
    0.06
    Act Density 0.030%

    No Known Activations