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

    Neuronpedia

    INDEX
    Explanations

    source of advice or criticism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RestorePolicy
    0.38
    ffee
    0.38
     حالی
    0.37
     davon
    0.37
    ૂર
    0.37
     પૈ
    0.36
    சிற
    0.36
     गौरतलब
    0.35
     빼
    0.35
    nitř
    0.34
    POSITIVE LOGITS
     from
    1.12
    from
    1.12
    จาก
    1.09
    来自
    1.03
     từ
    1.02
    來自
    1.02
     från
    1.00
     kutoka
    0.96
     от
    0.89
     από
    0.88
    Act Density 0.039%

    No Known Activations