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

    Neuronpedia

    INDEX
    Explanations

    breakdown for informational

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    0.49
    ip
    0.48
    ib
    0.46
    kkal
    0.46
    ri
    0.45
    okkal
    0.44
    ny
    0.44
    af
    0.44
    berg
    0.44
    Adv
    0.44
    POSITIVE LOGITS
    澧
    0.51
     macchina
    0.50
     اضافہ
    0.50
    ⺌
    0.49
     vanes
    0.48
    လေ
    0.48
    ランチ
    0.47
    ประโยชน์
    0.47
     informações
    0.46
    さらに
    0.46
    Act Density 0.000%

    No Known Activations