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

    Neuronpedia

    INDEX
    Explanations

    Efficient Routing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pend
    0.41
     ප
    0.41
    Cartoon
    0.41
    ūt
    0.40
     법
    0.39
    Architecture
    0.39
     가는
    0.38
    bora
    0.38
    lust
    0.37
    ướ
    0.36
    POSITIVE LOGITS
     subunits
    0.37
     заключа
    0.35
     encargado
    0.35
     Crust
    0.34
    ભગ
    0.34
     eau
    0.34
     эффективность
    0.33
     FSH
    0.33
    優勝
    0.33
     specified
    0.33
    Act Density 0.000%

    No Known Activations