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

    Neuronpedia

    INDEX
    Explanations

    defining scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.67
    ди
    0.64
    ä
    0.62
    å
    0.62
    ی
    0.61
    ᆹ
    0.61
    ί
    0.60
    с
    0.59
    る
    0.57
    ве
    0.57
    POSITIVE LOGITS
    it
    0.70
    '
    0.59
     desktop
    0.59
    n
    0.59
     remake
    0.59
     Desktop
    0.57
     Daytona
    0.56
    -
    0.56
     otom
    0.55
     depository
    0.55
    Act Density 0.010%

    No Known Activations