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

    Neuronpedia

    INDEX
    Explanations

    community

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Instruction
    -0.07
     Colonel
    -0.07
     *>
    -0.07
    amina
    -0.07
    _customize
    -0.07
    ابر
    -0.06
    وض
    -0.06
     menor
    -0.06
     "%.
    -0.06
     Ventura
    -0.06
    POSITIVE LOGITS
    随时
    0.08
    される
    0.07
     deactivated
    0.07
    被称为
    0.07
    Variant
    0.07
    遇到了
    0.07
     unzip
    0.07
     failures
    0.07
    的好处
    0.07
     і
    0.07
    Act Density 0.002%

    No Known Activations