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

    Neuronpedia

    INDEX
    Explanations

    punctuation and special characters

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

    code closing and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.84
     snippetHide
    -0.70
     Majefty
    -0.63
    jspb
    -0.63
     poffe
    -0.62
     ſta
    -0.62
    AddTagHelper
    -0.61
    ſelves
    -0.61
     незавершена
    -0.59
    ----</
    -0.58
    POSITIVE LOGITS
    ↵↵
    0.53
    ↵↵↵↵
    0.45
    <tr>
    0.45
     
    0.43
    <h2>
    0.40
    ↵↵↵
    0.39
    <bos>
    0.39
    <h5>
    0.38
    ↵↵↵↵↵
    0.38
    2
    0.38
    Act Density 0.001%

    No Known Activations