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

    Neuronpedia

    INDEX
    Explanations

    matplotlib code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lineWidth
    -0.07
    纛
    -0.07
     jq
    -0.07
    Af
    -0.06
    バ
    -0.06
    ARSER
    -0.06
     Door
    -0.06
    ItemClickListener
    -0.06
     Tie
    -0.06
    dire
    -0.06
    POSITIVE LOGITS
    (output
    0.08
    .props
    0.08
    ご紹介
    0.07
    内外
    0.07
    .management
    0.07
     חיפה
    0.07
    rowsing
    0.07
    .Split
    0.07
     locus
    0.07
    character
    0.07
    Act Density 0.009%

    No Known Activations