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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ified
    -0.07
    	friend
    -0.07
     roommate
    -0.06
    .exec
    -0.06
    (sec
    -0.06
    เขต
    -0.06
    reasonable
    -0.06
    卓
    -0.06
    ersiz
    -0.06
    umsuz
    -0.06
    POSITIVE LOGITS
    insn
    0.07
    眉
    0.06
    <G
    0.06
     Müş
    0.06
    'ye
    0.06
    756
    0.06
    announcement
    0.06
     conservatism
    0.06
     виконання
    0.06
     Blaze
    0.06
    Act Density 0.064%

    No Known Activations