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

    Neuronpedia

    INDEX
    Explanations

    certain structural elements related to organization and categorization in texts

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

    Tokens enclosed in parentheses

    np_acts-logits-general · gemini-2.0-flash

    section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    èdia
    -0.94
    RenderAtEndOf
    -0.89
    WebServlet
    -0.88
     '\\;'
    -0.80
    tvguidetime
    -0.79
     ComVisible
    -0.79
    ResumeLayout
    -0.77
     متعلقه
    -0.77
    Viitteet
    -0.76
    endphp
    -0.75
    POSITIVE LOGITS
    ​
    0.96
    <eos>
    0.89
    <strong>
    0.84
    ↵
    0.81
    <h3>
    0.74
    <b>
    0.70
    Click
    0.69
    <h5>
    0.69
    ‍
    0.68
                                   
    0.65
    Act Density 0.218%

    No Known Activations