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

    Neuronpedia

    INDEX
    Explanations

    alternative history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dha
    0.41
    consciously
    0.40
     soov
    0.39
     чы
    0.38
     விளக்கம்
    0.38
     keyValue
    0.37
     henkil
    0.37
    чы
    0.37
    เช่น
    0.37
    erry
    0.36
    POSITIVE LOGITS
     زین
    0.43
    lename
    0.43
    PostConstruct
    0.41
    名稱
    0.41
     margin
    0.40
    裱
    0.40
     erreicht
    0.39
    䂝
    0.39
    Name
    0.39
     déficit
    0.38
    Act Density 0.000%

    No Known Activations