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

    Neuronpedia

    INDEX
    Explanations

    software user interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    425
    -0.07
    kre
    -0.06
     grams
    -0.06
    Nil
    -0.06
    ạng
    -0.06
    '/
    -0.06
     będzie
    -0.06
    quil
    -0.06
    혼
    -0.06
     lives
    -0.06
    POSITIVE LOGITS
    アメリカ
    0.07
     ear
    0.06
     Glasses
    0.06
    igt
    0.06
     Rudy
    0.06
     reife
    0.06
     curved
    0.06
     شک
    0.06
    ้าค
    0.06
    Dear
    0.06
    Act Density 0.019%

    No Known Activations