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

    Neuronpedia

    INDEX
    Explanations

    collections, lists, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kolek
    0.39
     collecte
    0.39
     коллекции
    0.39
    ⵕ
    0.38
    क्वल
    0.38
    젯
    0.38
    飪
    0.38
     Elektrokh
    0.37
    संस्करण
    0.36
     स्वचालित
    0.36
    POSITIVE LOGITS
    0.45
    Think
    0.41
    Impossible
    0.39
    It
    0.39
    Imag
    0.39
    Almost
    0.39
    When
    0.38
     Almost
    0.38
    There
    0.38
     Believe
    0.37
    Act Density 0.001%

    No Known Activations