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

    Neuronpedia

    INDEX
    Explanations

    medical operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     normaux
    -1.20
     médec
    -1.16
     enfans
    -1.15
     ainfi
    -1.13
     feroit
    -1.12
     avoient
    -1.11
     zijne
    -1.09
     colorés
    -1.09
     étoient
    -1.09
     mijne
    -1.09
    POSITIVE LOGITS
     est
    0.61
     es
    0.60
     par
    0.59
     S
    0.58
     type
    0.56
     bar
    0.56
     ra
    0.54
     M
    0.52
     inter
    0.52
     group
    0.52
    Act Density 0.343%

    No Known Activations