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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating cause and effect relationships

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

    Follows punctuation or a formal reference

    np_acts-logits-general · gemini-2.0-flash

    source or writer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -1.04
     متعلقه
    -1.02
    Viitteet
    -0.98
    Демографія
    -0.96
    verwijspagina
    -0.90
    ✨:
    -0.90
    WriteBarrier
    -0.89
    AlterField
    -0.89
     Paglinawan
    -0.89
     jsPsych
    -0.89
    POSITIVE LOGITS
    <eos>
    1.14
    Source
    0.85
    <i>
    0.84
    <em>
    0.83
     Source
    0.76
    source
    0.67
     source
    0.67
     SOURCE
    0.61
     writer
    0.61
    来源
    0.60
    Act Density 0.136%

    No Known Activations