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

    Neuronpedia

    INDEX
    Explanations

    identifying categories of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ví
    0.45
     nutzt
    0.45
     teeth
    0.43
     vortices
    0.43
     toxin
    0.42
     eigenfunctions
    0.42
     পরিচয়
    0.41
    介紹
    0.41
     bootstrapping
    0.41
     montre
    0.40
    POSITIVE LOGITS
     Written
    0.46
     милли
    0.45
     политики
    0.45
    askan
    0.44
     written
    0.43
    acje
    0.43
     Yamaha
    0.43
     Moda
    0.42
    written
    0.41
    rika
    0.41
    Act Density 0.001%

    No Known Activations