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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating the presence or absence of specific features or characteristics

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

    Word before capitalized words

    np_acts-logits-general · gemini-2.0-flash

    conclusively characterized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.75
     Мексичка
    -0.71
     PhpStorm
    -0.68
    typeorm
    -0.66
    moveToFirst
    -0.62
     المعيارى
    -0.62
    PerformLayout
    -0.62
     Verdun
    -0.62
     Jefus
    -0.61
     OnInit
    -0.60
    POSITIVE LOGITS
     kasarigan
    0.61
    édi
    0.61
    Parity
    0.59
    ://$
    0.58
    互联网档案馆
    0.57
    دانشنامهٔ
    0.57
     banc
    0.57
    ève
    0.56
    CJK
    0.55
     Quo
    0.54
    Act Density 0.908%

    No Known Activations