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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wenn
    -0.09
     wohn
    -0.08
     Wochenende
    -0.08
    enteri
    -0.08
    leden
    -0.08
    ermin
    -0.07
    wann
    -0.07
     involucr
    -0.07
     ಪ್ರಶ್ನ
    -0.07
     basada
    -0.07
    POSITIVE LOGITS
     diluted
    0.09
     масштаб
    0.09
     mediums
    0.08
     nanti
    0.08
     dilute
    0.08
     cramped
    0.08
     dilution
    0.08
    Scaling
    0.08
    )?.
    0.08
     contexts
    0.08
    Act Density 0.015%

    No Known Activations