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

    Neuronpedia

    INDEX
    Explanations

    know what you don't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ہی
    0.65
    ີ
    0.64
    綣
    0.64
     acondicionado
    0.64
    дій
    0.62
     модуля
    0.61
    ificial
    0.61
    ިއ
    0.60
    ই
    0.59
    垡
    0.59
    POSITIVE LOGITS
     :
    0.63
     вместо
    0.60
     perceive
    0.59
     cherish
    0.57
    :
    0.57
     along
    0.57
     see
    0.56
     સહિત
    0.55
     think
    0.55
    :(
    0.54
    Act Density 0.042%

    No Known Activations