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

    Neuronpedia

    INDEX
    Explanations

    a variety of seemingly unrelated words including dates, locations, medical terminology and film related words.

    oai_token-act-pair · gemini-2.0-flash

    Sentence beginnings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.58
     autorytatywna
    -0.57
    󠁢
    -0.56
     emp
    -0.55
    libft
    -0.53
     post
    -0.53
    XmlEnum
    -0.52
    ->_
    -0.52
     resourceCulture
    -0.52
    </caption>
    -0.52
    POSITIVE LOGITS
    What
    0.75
    Have
    0.74
    In
    0.73
    We
    0.71
    When
    0.71
     traités
    0.71
     fermés
    0.70
    If
    0.69
     africains
    0.68
    On
    0.68
    Act Density 9.593%

    No Known Activations