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

    Neuronpedia

    INDEX
    Explanations

    code and data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Neville
    -0.07
    _up
    -0.07
    tfoot
    -0.06
    WAYS
    -0.06
    는지
    -0.06
     victory
    -0.06
     deadline
    -0.06
    mites
    -0.06
    amental
    -0.06
    Circle
    -0.06
    POSITIVE LOGITS
    df
    0.07
     ندارد
    0.06
     persever
    0.06
    -opt
    0.06
     三
    0.06
     Tar
    0.06
    ismus
    0.06
    ์เน
    0.06
    InnerHTML
    0.06
     Kont
    0.06
    Act Density 0.186%

    No Known Activations