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

    Neuronpedia

    INDEX
    Explanations

    key phrases that imply user preferences or experiences, particularly regarding media and technology

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

    preceding "normal"

    np_acts-logits-general · gemini-2.0-flash

    normal or nearly normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.81
    setVerticalGroup
    -0.59
    czegó
    -0.57
    wäh
    -0.56
     EconPapers
    -0.55
    brigens
    -0.54
     propOrder
    -0.53
     récente
    -0.52
    urably
    -0.52
    TableBody
    -0.51
    POSITIVE LOGITS
     normal
    3.64
    normal
    3.18
    Normal
    2.90
     normale
    2.82
     Normal
    2.76
     usual
    2.70
     NORMAL
    2.68
     ordinary
    2.65
     normalen
    2.62
     normales
    2.62
    Act Density 1.159%

    No Known Activations