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

    Neuronpedia

    INDEX
    Explanations

    Money/profits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sourceMapping
    -0.07
     hơi
    -0.06
     matters
    -0.06
     Đ
    -0.06
    áty
    -0.06
     Initialized
    -0.06
    으면
    -0.06
    ыт
    -0.06
    argar
    -0.06
    spawn
    -0.06
    POSITIVE LOGITS
     devastated
    0.07
    ンディ
    0.07
    ???↵↵
    0.06
    ゾ
    0.06
     commuters
    0.06
    */↵
    0.06
     colored
    0.06
    โช
    0.06
     $↵
    0.06
     high
    0.06
    Act Density 0.008%

    No Known Activations