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

    Neuronpedia

    INDEX
    Explanations

    references to writers or writing

    oai_token-act-pair · gemini-2.0-flash

    writer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.24
     feroit
    -1.19
     ainfi
    -1.16
     $_"
    -1.12
     '\\;'
    -1.11
     hâte
    -1.10
     avoient
    -1.09
     vectorielles
    -1.09
     auroit
    -1.08
     pouvoit
    -1.08
    POSITIVE LOGITS
    (
    0.84
    s
    0.83
    ↵
    0.80
    ing
    0.77
     
    0.72
    .
    0.71
    ,
    0.68
    /
    0.66
    w
    0.66
     (
    0.66
    Act Density 5.171%

    No Known Activations