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

    Neuronpedia

    INDEX
    Explanations

    sed commands with substitutions

    oai_token-act-pair · gemini-2.0-flash

    forward slash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esterday
    -0.77
     AssemblyCompany
    -0.70
     Lightboxes
    -0.67
    MLLoader
    -0.66
     Commencez
    -0.65
     tartalomajánló
    -0.65
     ddelweddau
    -0.64
    sidemargin
    -0.64
    GeneratedCode
    -0.64
     unknownFields
    -0.63
    POSITIVE LOGITS
    <bos>
    0.90
    '
    0.66
    (
    0.47
    -
    0.46
    "
    0.45
     "
    0.44
    The
    0.43
     saying
    0.42
    LabelTagHelper
    0.42
    ."
    0.41
    Act Density 3.854%

    No Known Activations