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

    Neuronpedia

    INDEX
    Explanations

    terms related to the initiation or start of events or processes

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

    commencement or commenced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ian
    -0.69
    er
    -0.68
    ia
    -0.67
    ed
    -0.67
    iyor
    -0.66
    o
    -0.65
    iis
    -0.64
    ek
    -0.64
    ie
    -0.62
    iar
    -0.61
    POSITIVE LOGITS
    <blockquote>
    0.35
    deinit
    0.35
    s
    0.35
    ت
    0.34
     habr
    0.34
    т
    0.34
    assemblée
    0.33
    싶
    0.33
    ρίζ
    0.33
     forest
    0.32
    Act Density 0.024%

    No Known Activations