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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ixon
    -0.06
    (iterator
    -0.06
    parency
    -0.06
    lapping
    -0.05
    [msg
    -0.05
     학생
    -0.05
    	gpio
    -0.05
    evt
    -0.05
    	Item
    -0.05
     tại
    -0.05
    POSITIVE LOGITS
     sympath
    0.08
    -linked
    0.07
    吹
    0.07
     recommendation
    0.07
     Able
    0.07
     equivalent
    0.07
     deline
    0.06
    _bias
    0.06
    ідно
    0.06
     wallpaper
    0.06
    Act Density 0.000%

    No Known Activations