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

    Neuronpedia

    INDEX
    Explanations

    academic course descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thursday
    -0.07
    (read
    -0.06
    /http
    -0.06
    construct
    -0.06
    최신
    -0.06
    aab
    -0.06
    ُون
    -0.06
     vlak
    -0.06
    。，
    -0.06
     cele
    -0.06
    POSITIVE LOGITS
    raits
    0.07
    .Throws
    0.07
     Αν
    0.07
     militant
    0.07
    Robin
    0.06
    <Object
    0.06
     Associ
    0.06
    navbarDropdown
    0.06
     l�
    0.06
    ~-~-~-~-
    0.06
    Act Density 0.035%

    No Known Activations