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

    Neuronpedia

    INDEX
    Explanations

    machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.96
    Мы
    0.89
    Durante
    0.83
    Finalmente
    0.83
     desenvolv
    0.82
    Лу
    0.81
     двигателя
    0.80
    кі
    0.79
    Quando
    0.79
     mécanismes
    0.79
    POSITIVE LOGITS
    ە
    1.09
     can
    1.02
    ur
    1.01
    u
    0.97
     It
    0.96
     Machine
    0.96
    n
    0.95
    z
    0.95
    uk
    0.91
    ü
    0.91
    Act Density 0.018%

    No Known Activations