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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DSP
    1.33
    বৃত্তি
    1.31
    _{-}^{
    1.28
    al
    1.23
     delights
    1.20
    amort
    1.20
    同时
    1.20
    TA
    1.18
     ultras
    1.17
     учи
    1.17
    POSITIVE LOGITS
    𝒊
    1.72
    𝒓
    1.66
     Lordships
    1.56
    ੁ
    1.46
    𝒖
    1.45
    iaan
    1.41
     heut
    1.40
    ि
    1.38
    𝒋
    1.35
     jeweiligen
    1.34
    Act Density 0.053%

    No Known Activations