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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tính
    -0.07
    <Texture
    -0.07
     protect
    -0.07
     הייתי
    -0.07
     tối
    -0.07
    鱼类
    -0.07
    翻开
    -0.06
    שיפור
    -0.06
    ınızı
    -0.06
     Outlook
    -0.06
    POSITIVE LOGITS
    phant
    0.07
    :&
    0.07
    М
    0.07
    什
    0.07
     ")
    0.06
     Lak
    0.06
    OfType
    0.06
    ppe
    0.06
    哪
    0.06
    够
    0.06
    Act Density 0.004%

    No Known Activations