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

    Neuronpedia

    INDEX
    Explanations

    mathematical methods and filters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    na
    0.50
    '
    0.49
    rp
    0.48
    re
    0.47
    no
    0.47
    el
    0.47
    rs
    0.46
    aa
    0.46
    new
    0.45
    issue
    0.44
    POSITIVE LOGITS
     Yakima
    0.50
     etkin
    0.46
    柑
    0.44
    드의
    0.43
     вимо
    0.43
     расши
    0.42
    坭
    0.42
     величе
    0.42
    𝐌
    0.42
     автомобиля
    0.41
    Act Density 0.004%

    No Known Activations