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

    Neuronpedia

    INDEX
    Explanations

    Output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Apprent
    -0.07
     brushes
    -0.07
     EZ
    -0.07
    めて
    -0.06
    调整
    -0.06
     прин
    -0.06
    并
    -0.06
     siêu
    -0.06
     chaining
    -0.06
    issen
    -0.06
    POSITIVE LOGITS
    \<^
    0.08
    lectric
    0.07
     disastrous
    0.06
     bios
    0.06
     Medina
    0.06
     hmot
    0.06
    plt
    0.06
    電話
    0.06
    екту
    0.06
    mutations
    0.06
    Act Density 0.025%

    No Known Activations