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

    Neuronpedia

    INDEX
    Explanations

    Website code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .swap
    -0.08
    	element
    -0.08
     creep
    -0.07
    swing
    -0.07
     Browser
    -0.07
     economies
    -0.07
    8
    -0.07
    onedDateTime
    -0.07
     Wedding
    -0.07
    écoute
    -0.06
    POSITIVE LOGITS
    o
    0.08
     הו
    0.08
    行动
    0.07
    :no
    0.07
     proto
    0.07
    חו
    0.07
    oro
    0.07
     Auto
    0.07
    ito
    0.07
     никто
    0.07
    Act Density 0.551%

    No Known Activations