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

    Neuronpedia

    INDEX
    Explanations

    spanish or french words related to describing or explaining processes and giving directions to someone

    oai_token-act-pair · gemini-2.0-flash

    Spanish and French text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoient
    -1.70
     feroit
    -1.64
     colorés
    -1.63
     réguli
    -1.60
     varandra
    -1.59
     sauvages
    -1.59
     normaux
    -1.59
     étoient
    -1.58
     actuels
    -1.57
     auroit
    -1.56
    POSITIVE LOGITS
     un
    1.01
     one
    0.94
     con
    0.90
     grand
    0.88
     all
    0.88
     en
    0.87
     cor
    0.85
     par
    0.85
     man
    0.85
     a
    0.84
    Act Density 0.947%

    No Known Activations