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

    Neuronpedia

    INDEX
    Explanations

    specific names and titles related to music, opera, or performance works

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

    proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.68
     Gegenteil
    -0.58
     Wikiseite
    -0.58
    intios
    -0.58
    Diweddarwch
    -0.54
     '\\;'
    -0.53
    ConstraintMaker
    -0.52
     ويكيپيديا
    -0.52
    OGND
    -0.52
     kasarigan
    -0.50
    POSITIVE LOGITS
     Dra
    0.49
     Fran
    0.47
     Gig
    0.44
     Sit
    0.44
    Dra
    0.44
     Flu
    0.43
     Fore
    0.42
     Teles
    0.42
     Bir
    0.42
     Ris
    0.42
    Act Density 0.220%

    No Known Activations