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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly emphasizing periods, and their context in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or configuration file fragments

    np_acts-logits-general · gemini-2.0-flash

    periods and closing bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.78
    ↵↵
    -0.73
    OrBuilder
    -0.66
     '';
    -0.59
     "";
    -0.56
    "));
    -0.55
    ";
    -0.52
    awtextra
    -0.51
     {};
    -0.50
    '));
    -0.48
    POSITIVE LOGITS
     resourceCulture
    0.69
    PINES
    0.61
     HttpNotFound
    0.60
    PreferredItem
    0.60
    RetVal
    0.60
     (.
    0.60
    _.
    0.58
    LLocation
    0.58
     confronti
    0.58
    ™.
    0.58
    Act Density 0.451%

    No Known Activations