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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pos
    -0.07
    :[↵
    -0.07
     Hed
    -0.06
    _HDR
    -0.06
     swaps
    -0.06
    ynamic
    -0.06
    drink
    -0.06
    आ
    -0.06
     Temper
    -0.06
     robots
    -0.06
    POSITIVE LOGITS
    .quote
    0.07
    ("</
    0.07
     quanto
    0.07
     generates
    0.06
    .toLocale
    0.06
     işlemi
    0.06
    合格
    0.06
     fray
    0.06
     seiner
    0.06
     През
    0.06
    Act Density 0.073%

    No Known Activations