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

    Neuronpedia

    INDEX
    Explanations

    descriptive words in a disturbing, ghostly scene

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.73
    tvguidetime
    -0.62
     entertained
    -0.50
     greatly
    -0.49
    gebra
    -0.49
    Revenir
    -0.49
     [#
    -0.47
     pleasantly
    -0.46
     incredibly
    -0.46
    tagHelper
    -0.45
    POSITIVE LOGITS
    <bos>
    0.60
    SizeF
    0.55
    UnusedPrivate
    0.54
    xaml
    0.53
    XmlAccessorType
    0.53
    HasAnnotation
    0.53
     Référence
    0.51
     lccn
    0.50
    cur
    0.50
    cshtml
    0.50
    Act Density 2.932%

    No Known Activations