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

    Neuronpedia

    INDEX
    Explanations

    code block endings

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    code concluding tags and snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.88
     myſelf
    -0.87
     '\\;'
    -0.84
    الدراسه
    -0.78
     itſelf
    -0.78
     Jefus
    -0.74
    Története
    -0.74
     doubtnut
    -0.72
     Efq
    -0.72
     ſtate
    -0.71
    POSITIVE LOGITS
    else
    0.66
    </code>
    0.59
    <unused60>
    0.57
    <eos>
    0.53
     else
    0.52
    </em>
    0.52
     amor
    0.50
     */
    0.49
    <unused61>
    0.48
    ↵↵↵↵
    0.47
    Act Density 0.098%

    No Known Activations