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

    Neuronpedia

    INDEX
    Explanations

    mathematical text paired with bracketed and unbracketed "and" or "or"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     already
    -0.06
     ïĤ
    -0.06
     Hä
    -0.06
    âĢª
    -0.06
    æĽ´å¤ļ
    -0.06
    ARRANT
    -0.06
    orrent
    -0.06
    æ¥Ń
    -0.06
    upp
    -0.06
    presso
    -0.06
    POSITIVE LOGITS
     quite
    0.14
     Quite
    0.12
    quite
    0.12
    quad
    0.08
    Quite
    0.08
    iem
    0.07
     Clair
    0.07
    uitka
    0.07
     quit
    0.07
    ::.
    0.07
    Act Density 0.013%

    No Known Activations