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

    Neuronpedia

    INDEX
    Explanations

    fun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ในร
    -0.07
    оді
    -0.07
     concrete
    -0.06
     risen
    -0.06
    _allocated
    -0.06
     Wir
    -0.06
    =file
    -0.06
    ‏
    -0.06
     Bureau
    -0.06
     artistic
    -0.06
    POSITIVE LOGITS
     amen
    0.07
    PATCH
    0.06
     그래
    0.06
    除
    0.06
     tomto
    0.06
     Repair
    0.06
     下跌
    0.06
     ít
    0.06
     đai
    0.06
    MER
    0.06
    Act Density 0.130%

    No Known Activations