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

    Neuronpedia

    INDEX
    Explanations

    references to normalcy and typical experiences

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

    normal or typical conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GetMapping
    -0.40
    此次
    -0.35
     onderzoek
    -0.35
    BuildContext
    -0.35
     submission
    -0.34
     Zusch
    -0.34
    とこ
    -0.33
     Magn
    -0.33
     blotting
    -0.32
    徜
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.80
     normalidad
    0.79
     Савезне
    0.69
     rhestr
    0.66
    delwed
    0.61
     CreateTagHelper
    0.61
     normale
    0.60
     <>",
    0.59
     normales
    0.58
     típica
    0.58
    Act Density 0.021%

    No Known Activations