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

    Neuronpedia

    INDEX
    Explanations

    French words and words used in French conversation.

    oai_token-act-pair · gemini-2.0-flash

    French prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -1.03
    )];
    -0.69
     this
    -0.65
    ########.
    -0.60
     these
    -0.60
     its
    -0.59
     his
    -0.59
     mergeFrom
    -0.59
    />,
    -0.59
     EconPapers
    -0.58
    POSITIVE LOGITS
     prochaines
    0.66
     âmes
    0.66
     têtes
    0.64
     lèvres
    0.63
     larmes
    0.62
     preuves
    0.61
     ladite
    0.60
     nourrir
    0.60
     cœurs
    0.59
     tacón
    0.59
    Act Density 2.017%

    No Known Activations