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

    Neuronpedia

    INDEX
    Explanations

    providing links and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heresy
    1.05
     ਅਤੇ
    1.04
     ravaged
    1.03
    而在
    1.03
     සහ
    1.01
     এবং
    1.00
    ocide
    1.00
     condemning
    0.99
     और
    0.95
     rebuke
    0.93
    POSITIVE LOGITS
    я
    1.07
    个数
    1.05
    ️
    0.94
     целый
    0.91
    $$
    0.91
    0
    0.87
    ประจำ
    0.86
     colorful
    0.84
    们
    0.83
    ت
    0.83
    Act Density 0.001%

    No Known Activations