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

    Neuronpedia

    INDEX
    Explanations

    random state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infrastructure
    0.38
     injective
    0.37
     trifle
    0.37
     වූ
    0.36
     CONCLUSION
    0.36
    Ր
    0.36
     borrows
    0.36
     advanced
    0.36
     záv
    0.36
     appreciative
    0.35
    POSITIVE LOGITS
    Anne
    0.46
    Okno
    0.42
    の場合
    0.39
     casque
    0.38
     pesquisa
    0.37
     ditch
    0.37
    佲
    0.36
     voitures
    0.36
    窓
    0.36
     ringing
    0.35
    Act Density 0.000%

    No Known Activations