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

    Neuronpedia

    INDEX
    Explanations

    listing numbers and facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGLE
    0.43
     địch
    0.42
    डेजा
    0.42
    양이
    0.41
    닼
    0.41
    자가
    0.40
    无人
    0.40
    మణ
    0.40
    疥
    0.40
     ignor
    0.39
    POSITIVE LOGITS
     まず
    0.43
    ous
    0.43
     bordo
    0.42
     計算
    0.41
     nuovo
    0.40
    interactive
    0.40
     食
    0.40
    ricao
    0.40
    acao
    0.40
     concerted
    0.40
    Act Density 0.001%

    No Known Activations