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

    Neuronpedia

    INDEX
    Explanations

    exchange

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _extent
    -0.06
     its
    -0.06
    (skill
    -0.06
    _losses
    -0.06
     факт
    -0.06
    .logging
    -0.06
    -d
    -0.06
    	L
    -0.06
    Pure
    -0.06
    igan
    -0.06
    POSITIVE LOGITS
     exchange
    0.17
     Exchange
    0.12
     exchanges
    0.10
    交流
    0.09
     alış
    0.09
    Exchange
    0.07
    exchange
    0.07
     Praha
    0.07
    ,col
    0.06
    (display
    0.06
    Act Density 0.007%

    No Known Activations