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

    Neuronpedia

    INDEX
    Explanations

    -->

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iram
    -0.06
    -li
    -0.06
     році
    -0.06
    .Queue
    -0.06
     비
    -0.06
    ahas
    -0.05
    وية
    -0.05
     locker
    -0.05
     Bram
    -0.05
     成
    -0.05
    POSITIVE LOGITS
    γή
    0.07
     »,
    0.07
    �
    0.07
    quite
    0.07
    .protobuf
    0.07
    esseract
    0.06
     car
    0.06
    �单
    0.06
     surtout
    0.06
    ปก
    0.06
    Act Density 0.009%

    No Known Activations