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

    Neuronpedia

    INDEX
    Explanations

    add to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     additional
    0.57
     thêm
    0.55
     adicional
    0.49
     további
    0.48
    附加
    0.46
    额外的
    0.46
    z
    0.45
    additional
    0.45
    i
    0.43
    เพิ่มเติม
    0.43
    POSITIVE LOGITS
     ala
    0.49
     Ala
    0.48
    AfterTax
    0.45
    Su
    0.43
    Ala
    0.43
    ॅमिली
    0.43
     سو
    0.41
    தால்
    0.41
    㑹
    0.41
    ભાર
    0.40
    Act Density 0.043%

    No Known Activations