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

    Neuronpedia

    INDEX
    Explanations

    bot conversations and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ourselves
    -0.06
    _STRIP
    -0.06
     땅
    -0.06
    _CY
    -0.06
     fragmentManager
    -0.06
    trained
    -0.06
    standing
    -0.06
    ict
    -0.06
    .cod
    -0.06
     stretches
    -0.06
    POSITIVE LOGITS
     giải
    0.07
    �
    0.07
     установ
    0.06
    .lu
    0.06
    esser
    0.06
    чна
    0.06
     غ
    0.06
     Ã
    0.06
    ∏
    0.06
     ứng
    0.06
    Act Density 0.018%

    No Known Activations