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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lamaz
    -0.07
     bites
    -0.06
     elsewhere
    -0.06
    оди
    -0.06
    .assertj
    -0.06
     Bard
    -0.06
    _mon
    -0.06
     areas
    -0.06
    igrants
    -0.06
    これ
    -0.06
    POSITIVE LOGITS
     У
    0.07
     نقل
    0.06
     موس
    0.06
     clearing
    0.06
    (milliseconds
    0.06
     Mention
    0.06
    �
    0.06
    и
    0.06
    ur
    0.06
    идента
    0.06
    Act Density 0.006%

    No Known Activations