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

    Neuronpedia

    INDEX
    Explanations

    states or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁢</
    0.46
    frameNStart
    0.43
     INVENTION
    0.42
     ngoài
    0.41
     eğer
    0.41
     playerData
    0.41
     Parad
    0.40
     компью
    0.40
     Filtr
    0.40
    疚
    0.40
    POSITIVE LOGITS
    ఊ
    0.45
     class
    0.45
    class
    0.42
    Kit
    0.40
    Respect
    0.39
    Relax
    0.39
    Demon
    0.38
    Sweden
    0.38
     tĩnh
    0.38
    ->
    0.37
    Act Density 0.000%

    No Known Activations