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

    Neuronpedia

    INDEX
    Explanations

    numeric representations of years

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

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infór
    -0.68
    AndEndTag
    -0.58
     surla
    -0.57
     menopause
    -0.56
     democracia
    -0.56
    orced
    -0.55
    ValueStyle
    -0.54
    ंदीखरीदारी
    -0.54
     bénéficiaire
    -0.53
     dezelve
    -0.52
    POSITIVE LOGITS
     IKEA
    0.39
    ITECH
    0.39
    свя
    0.38
    googleapis
    0.36
    кей
    0.36
     Hacking
    0.36
     ANZ
    0.36
     AR
    0.35
     Jake
    0.35
     PN
    0.35
    Act Density 0.081%

    No Known Activations