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

    Neuronpedia

    INDEX
    Explanations

    appellee/appellants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ainfi
    -1.59
     feroit
    -1.58
     étoient
    -1.54
     avoient
    -1.52
     plufieurs
    -1.48
     pouvoit
    -1.41
     auroit
    -1.40
     mauva
    -1.38
     démocr
    -1.37
     religieuses
    -1.36
    POSITIVE LOGITS
     
    1.04
     a
    0.93
     in
    0.90
     (
    0.90
     the
    0.89
     and
    0.89
     of
    0.87
     an
    0.83
     l
    0.83
     all
    0.83
    Act Density 0.139%

    No Known Activations