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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant achievements or first occurrences

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

    "...for the first time..."

    np_acts-logits-general · gemini-2.0-flash

    first time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دیکھیے
    -0.65
    Дереккөздер
    -0.53
    графія
    -0.51
    Personendaten
    -0.49
    — 
    -0.49
    ->___
    -0.48
     كرد
    -0.46
    ℚ
    -0.46
    ďaka
    -0.45
     deur
    -0.45
    POSITIVE LOGITS
    HtmlAttribute
    1.13
     betweenstory
    0.97
    RenderAtEndOf
    0.94
    TagMode
    0.83
    tvguidetime
    0.78
    complexContent
    0.74
     ujednoznacz
    0.73
    DebuggerNonUser
    0.72
    expandindo
    0.72
    __*/
    0.70
    Act Density 0.472%

    No Known Activations