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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Duel
    -0.08
     hopeful
    -0.08
    .Price
    -0.07
    杜绝
    -0.07
     เมษายน
    -0.07
    urd
    -0.06
     Quiet
    -0.06
    .getStart
    -0.06
    そう
    -0.06
    史诗
    -0.06
    POSITIVE LOGITS
    Tiny
    0.08
    く
    0.08
    (parse
    0.07
    frame
    0.07
    zano
    0.07
    إمكانية
    0.07
    くて
    0.07
    iability
    0.07
    hci
    0.07
    :x
    0.07
    Act Density 0.014%

    No Known Activations