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

    Neuronpedia

    INDEX
    Explanations

    free version or paid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Postfix
    0.52
    ajul
    0.44
     QtWidgets
    0.42
    OfType
    0.42
    üller
    0.42
    தல
    0.42
    ModelGrid
    0.42
    henyl
    0.41
    apiUrl
    0.41
    édéric
    0.40
    POSITIVE LOGITS
    dib
    0.50
    會員
    0.48
     szyb
    0.46
     ರೈ
    0.44
    ام
    0.44
     bike
    0.43
     mills
    0.43
    diesel
    0.43
    law
    0.43
    印度
    0.43
    Act Density 0.005%

    No Known Activations