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

    Neuronpedia

    INDEX
    Explanations

    HTML and JavaScript code structure elements

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

    HTML structure (`<start_of_turn>`, `body`, `div`, `script`, `endsection`) and `user` text indicator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.74
    ########.
    -0.72
    出版年
    -0.66
     consultato
    -0.61
    addPreferredGap
    -0.60
    󠁬
    -0.59
    <unused14>
    -0.58
    <unused74>
    -0.58
    <unused8>
    -0.58
    [@BOS@]
    -0.58
    POSITIVE LOGITS
    zeptember
    0.34
    endsection
    0.31
    Extra
    0.30
    extra
    0.30
     extra
    0.30
     next
    0.29
     Extra
    0.29
     abz
    0.29
    qrstuvwxyz
    0.29
    next
    0.28
    Act Density 0.011%

    No Known Activations