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

    Neuronpedia

    INDEX
    Explanations

    birth and death dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    1.06
    اد
    0.92
    ק
    0.90
    ి
    0.87
    z
    0.85
    णी
    0.84
    ॉन
    0.84
    ac
    0.82
    י
    0.81
    ↵↵
    0.80
    POSITIVE LOGITS
    to
    1.06
     созда
    0.99
     were
    0.96
     были
    0.96
     игра
    0.94
     dejaron
    0.94
     выяв
    0.92
     разработан
    0.91
     уви
    0.90
     военно
    0.90
    Act Density 0.009%

    No Known Activations