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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reactions
    -0.07
     άλλ
    -0.07
     factorial
    -0.07
    _EQ
    -0.06
    Wie
    -0.06
    /loader
    -0.06
    ек
    -0.06
    _identifier
    -0.06
     Variation
    -0.06
    -desc
    -0.06
    POSITIVE LOGITS
     consumes
    0.06
     García
    0.06
    holder
    0.06
    рана
    0.06
    ический
    0.06
    لب
    0.06
     scenarios
    0.06
     〉
    0.06
     '">
    0.06
     prevents
    0.06
    Act Density 0.003%

    No Known Activations