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

    Neuronpedia

    INDEX
    Explanations

    first person and pronouns but seems very noisy

    oai_token-act-pair · gemini-2.0-flash

    sale/selling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -0.58
    يكب
    -0.54
    تفصیلات
    -0.54
    ynchrotron
    -0.53
    Hentet
    -0.49
    Obrázky
    -0.49
    libft
    -0.48
    Scheduling
    -0.48
    vatar
    -0.47
    windig
    -0.47
    POSITIVE LOGITS
     sale
    2.20
     sell
    2.14
     selling
    2.09
     sold
    2.08
     sells
    1.88
    Sale
    1.86
     Sale
    1.86
    sale
    1.85
     Sell
    1.82
    sold
    1.81
    Act Density 2.821%

    No Known Activations