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

    Neuronpedia

    INDEX
    Explanations

    scientific publication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pon
    -0.07
     Wyn
    -0.06
    нику
    -0.06
    -alpha
    -0.06
     Eden
    -0.06
     peaks
    -0.06
     Gloss
    -0.06
     Isa
    -0.06
    명을
    -0.06
     зуст
    -0.06
    POSITIVE LOGITS
    (se
    0.07
    σκευή
    0.06
    Trash
    0.06
     evacuate
    0.06
    /cms
    0.06
     cuenta
    0.06
    _reverse
    0.06
    786
    0.06
    ське
    0.06
    رت
    0.06
    Act Density 0.010%

    No Known Activations