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

    Neuronpedia

    INDEX
    Explanations

    scientific names, organizations, backgrounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Бей
    0.41
     energ
    0.38
     pin
    0.37
    ከር
    0.37
    อาด
    0.37
    Month
    0.37
     requirement
    0.37
     మే
    0.37
     ин
    0.36
    bert
    0.36
    POSITIVE LOGITS
     ramas
    0.42
     dovuto
    0.40
     dalla
    0.40
    ]}/${
    0.39
    ">\
    0.39
    ষ্
    0.38
    rı
    0.38
    槭
    0.38
     trovato
    0.38
     explicado
    0.38
    Act Density 0.002%

    No Known Activations