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

    Neuronpedia

    INDEX
    Explanations

    shallow comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \,.
    0.65
    дони
    0.61
     desi
    0.60
     Ephesians
    0.60
     Zhejiang
    0.60
     Archived
    0.60
     financieras
    0.60
    \|_{
    0.59
    cheese
    0.59
    iteritems
    0.59
    POSITIVE LOGITS
    তার
    0.70
    তা
    0.65
    また
    0.62
     વખતે
    0.61
    े
    0.60
    và
    0.59
    olate
    0.56
    ный
    0.56
    ति
    0.55
    ія
    0.55
    Act Density 0.003%

    No Known Activations