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

    Neuronpedia

    INDEX
    Explanations

    descriptive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERC
    -0.06
     Stafford
    -0.06
    032
    -0.06
    	Output
    -0.06
     Deck
    -0.06
     Bou
    -0.06
    ляв
    -0.06
    ��
    -0.06
    ouncer
    -0.06
    .Manager
    -0.06
    POSITIVE LOGITS
     yıldır
    0.07
    ","
    0.06
    늘
    0.06
    About
    0.06
     ech
    0.06
     cig
    0.06
    :first
    0.06
     provoc
    0.06
     brid
    0.06
    (Route
    0.06
    Act Density 0.136%

    No Known Activations