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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to cultural or philosophical concepts

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

    idioms and proverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.48
     nahilalakip
    -0.46
    messer
    -0.45
     saar
    -0.45
    لينكات
    -0.44
    Aholisi
    -0.43
     Domini
    -0.42
     Tengah
    -0.42
    ffions
    -0.41
     hairc
    -0.41
    POSITIVE LOGITS
     HasFactory
    0.47
     couvercle
    0.40
     ['./
    0.39
    InputBorder
    0.39
     """",
    0.38
     defaultdict
    0.36
     electrónicos
    0.35
     aDecoder
    0.34
     requestCode
    0.34
     agresión
    0.33
    Act Density 0.017%

    No Known Activations