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

    Neuronpedia

    INDEX
    Explanations

    communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meals
    0.47
     associa
    0.46
    новни
    0.46
    ogeneous
    0.46
     nocturnal
    0.45
     setbacks
    0.43
    こ
    0.42
    od
    0.41
    grades
    0.41
    ab
    0.41
    POSITIVE LOGITS
     Если
    0.74
     если
    0.67
    <unused730>
    0.66
     состояние
    0.65
     nếu
    0.64
     Định
    0.64
     如果
    0.63
    Interestingly
    0.63
     क्वांटिटी
    0.63
     发布
    0.62
    Act Density 0.000%

    No Known Activations