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

    Neuronpedia

    INDEX
    Explanations

    structural elements and punctuation in the text

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

    End of sentences

    np_acts-logits-general · gemini-2.0-flash

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -1.14
     Saltar
    -0.94
     ModelExpression
    -0.83
     >=",
    -0.76
    InputTagHelper
    -0.71
     Савезне
    -0.70
    saraba
    -0.69
     MainAxisSize
    -0.68
     uLocal
    -0.67
    帖最后由
    -0.66
    POSITIVE LOGITS
    <eos>
    4.01
    ↵↵↵↵↵↵↵
    0.83
    ↵↵↵↵↵↵↵↵
    0.82
    ↵↵↵↵
    0.80
    "));
    0.79
    ↵↵↵↵↵↵↵↵↵↵↵
    0.78
    ↵↵↵↵↵↵↵↵↵
    0.78
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.77
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.77
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.76
    Act Density 1.263%

    No Known Activations