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

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manifestations
    -0.07
     lakh
    -0.07
    никами
    -0.07
    /client
    -0.07
    政
    -0.06
     Declaration
    -0.06
    _SUB
    -0.06
    _prediction
    -0.06
     crushing
    -0.06
    _Up
    -0.06
    POSITIVE LOGITS
     Joker
    0.07
     Jacksonville
    0.06
     Mage
    0.06
     Angeles
    0.06
    ろう
    0.06
    มข
    0.06
     ομά
    0.06
    .RecyclerView
    0.06
     здійсню
    0.06
    atures
    0.06
    Act Density 0.083%

    No Known Activations