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

    Neuronpedia

    INDEX
    Explanations

    numbers following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Highlighter
    0.20
     ArrayIndex
    0.20
     Benutz
    0.19
    escens
    0.18
     Thumbnail
    0.18
    AutoStabilise
    0.17
    ußer
    0.17
    rafpunkte
    0.17
    arankan
    0.17
     "?"
    0.17
    POSITIVE LOGITS
    이
    0.19
     population
    0.18
    ́
    0.18
    ч
    0.18
     национа
    0.17
    рин
    0.17
    ̄
    0.17
    у
    0.17
    č
    0.17
    с
    0.17
    Act Density 0.346%

    No Known Activations