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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Museum
    -0.07
    _weights
    -0.07
    키
    -0.07
    mtree
    -0.07
    pNext
    -0.06
     Payne
    -0.06
    进一步
    -0.06
     King
    -0.06
    Merit
    -0.06
    ourt
    -0.06
    POSITIVE LOGITS
    squ
    0.06
     alanında
    0.06
     Recomm
    0.06
    traditional
    0.06
     dw
    0.06
     vra
    0.06
    :'/
    0.06
    #",
    0.06
    $body
    0.06
    /mp
    0.06
    Act Density 0.019%

    No Known Activations