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

    Neuronpedia

    INDEX
    Explanations

    expressions related to cognitive processes and recalling thoughts

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

    come to mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.47
    principalColumn
    -0.47
    +#+
    -0.43
     HasFactory
    -0.41
     مشين
    -0.41
    wnież
    -0.40
    Erstellt
    -0.39
     yyl
    -0.38
    ябре
    -0.38
     careful
    -0.38
    POSITIVE LOGITS
     متعلقه
    0.48
    findpost
    0.47
     вспом
    0.46
     المثال
    0.45
    Географи
    0.44
    Попис
    0.40
     Recall
    0.40
    Recall
    0.40
     فريبيس
    0.39
    ponses
    0.38
    Act Density 0.138%

    No Known Activations