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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onya
    -0.07
    	sp
    -0.07
    ува
    -0.07
    ينا
    -0.07
    ави
    -0.06
     Alexandre
    -0.06
    >Name
    -0.06
     Afr
    -0.06
     cerca
    -0.06
    оти
    -0.06
    POSITIVE LOGITS
    (curr
    0.07
    	reset
    0.06
     ration
    0.06
     msgs
    0.06
    _ut
    0.06
     arrival
    0.06
     attained
    0.06
    ,input
    0.06
    (hours
    0.06
    btc
    0.06
    Act Density 0.020%

    No Known Activations