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

    Neuronpedia

    INDEX
    Explanations

    definitions and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಖರೀದ
    0.59
     मानसिक
    0.52
     якщо
    0.50
     Minds
    0.50
    нгтон
    0.50
    cticamente
    0.49
    ㅌ
    0.49
     Antworten
    0.49
    atória
    0.49
     свар
    0.49
    POSITIVE LOGITS
    水
    0.57
    主
    0.46
    与
    0.46
    三
    0.46
    Of
    0.46
    P
    0.45
    将
    0.45
     vatt
    0.44
     pending
    0.44
     ánh
    0.44
    Act Density 0.001%

    No Known Activations