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

    Neuronpedia

    INDEX
    Explanations

    fully open

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ani
    0.50
    ()
    0.48
    anie
    0.48
    )
    0.45
    anya
    0.44
    r
    0.44
    abelle
    0.43
     as
    0.43
     शिमला
    0.43
     )
    0.42
    POSITIVE LOGITS
     militaires
    0.47
    𝐧
    0.46
     Military
    0.43
    ської
    0.42
     فوجی
    0.42
    स्प
    0.42
    ыл
    0.42
     fondamentali
    0.42
     supervisory
    0.42
    كيف
    0.42
    Act Density 0.051%

    No Known Activations