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

    Neuronpedia

    INDEX
    Explanations

    numerical data and percentages

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

    "Percent" followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    percent followed by data or statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -1.02
    SizeF
    -0.97
     Paglinawan
    -0.95
     GenerationType
    -0.91
     مشين
    -0.89
    OGND
    -0.89
     Rosas
    -0.87
    ../../
    -0.87
     artefacts
    -0.87
    NamedQueries
    -0.87
    POSITIVE LOGITS
     gages
    0.89
     theaters
    0.85
     disks
    0.84
     Theaters
    0.82
     Stearns
    0.79
    ness
    0.79
    și
    0.78
    ی
    0.77
    Whiskey
    0.77
    Cuz
    0.76
    Act Density 0.851%

    No Known Activations