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

    Neuronpedia

    INDEX
    Explanations

    cryptography and directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esper
    0.45
     aph
    0.44
     Azi
    0.43
     jamás
    0.42
     longs
    0.41
     đã
    0.41
     azi
    0.40
     ethane
    0.40
     tracing
    0.40
     apat
    0.40
    POSITIVE LOGITS
    砰
    0.44
    Dil
    0.44
     효과
    0.42
     प्रभावशाली
    0.42
    收入
    0.42
    ꔰ
    0.42
    Corollary
    0.41
    Iteration
    0.41
     प्रभाव
    0.41
     অভিনয়ের
    0.41
    Act Density 0.001%

    No Known Activations