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

    Neuronpedia

    INDEX
    Explanations

    nylon walls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    અ
    0.45
    ObjectID
    0.43
    ফান
    0.42
    𝚏
    0.42
    eluarkan
    0.41
    ສ່ວນ
    0.41
     އި
    0.41
    óln
    0.40
     असंभव
    0.39
    URLException
    0.39
    POSITIVE LOGITS
     unit
    0.41
    牛肉
    0.39
     Sharpe
    0.39
     शर
    0.38
     শার
    0.38
     Unit
    0.37
     kabul
    0.36
     volta
    0.36
    Unit
    0.35
    ユニット
    0.35
    Act Density 0.000%

    No Known Activations