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

    Neuronpedia

    INDEX
    Explanations

    the phrase "as a"

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     as
    -0.77
     بيها
    -0.54
    šanai
    -0.51
     particulières
    -0.51
     colère
    -0.50
     russes
    -0.50
     appartiennent
    -0.48
     sauvages
    -0.48
     florales
    -0.47
     appartient
    -0.47
    POSITIVE LOGITS
     result
    0.90
    "])
    0.81
     consequence
    0.80
     Normdatei
    0.68
    EndGlobalSection
    0.67
     TextAppearance
    0.67
     RESULT
    0.66
    "]);
    0.65
    '][]
    0.64
    ₁)
    0.64
    Act Density 2.700%

    No Known Activations