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

    Neuronpedia

    INDEX
    Explanations

    various forms of quotation marks and apostrophes

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

    French quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.60
     CommonModule
    -0.57
    GOTREF
    -0.52
     defaultstate
    -0.52
     arşivlendi
    -0.52
     BoxFit
    -0.47
     separately
    -0.46
     pena
    -0.45
     consultato
    -0.43
    ξύ
    -0.42
    POSITIVE LOGITS
    $'
    0.60
    |'
    0.57
     noastră
    0.57
    s
    0.55
     noastre
    0.54
     idéia
    0.54
     senhora
    0.52
    loč
    0.52
     jagung
    0.52
    ]'
    0.52
    Act Density 0.069%

    No Known Activations