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

    Neuronpedia

    INDEX
    Explanations

    function signatures and code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ছি
    0.64
     act
    0.63
     ঝাঁপ
    0.56
     Act
    0.54
    Фи
    0.54
    锋
    0.53
     न्यायाधीश
    0.53
    слежи
    0.52
     have
    0.52
     acts
    0.52
    POSITIVE LOGITS
    belief
    0.78
     desiring
    0.75
    ):
    0.75
    )$:
    0.75
     тог
    0.75
    Request
    0.75
     ønsker
    0.74
     っ
    0.74
    requests
    0.74
    .):
    0.74
    Act Density 0.757%

    No Known Activations