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

    Neuronpedia

    INDEX
    Explanations

    internal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ancora
    -0.08
    (*)
    -0.06
     sonra
    -0.06
    plings
    -0.06
    ersions
    -0.06
    Yahoo
    -0.06
     commodo
    -0.06
     тоді
    -0.06
    _normal
    -0.06
    icerca
    -0.06
    POSITIVE LOGITS
    ۱۹۵
    0.06
     кін
    0.06
     mindset
    0.06
     Apost
    0.06
     буд
    0.06
     उस
    0.06
     جی
    0.06
    陷
    0.06
     ":
    0.06
    /web
    0.06
    Act Density 0.001%

    No Known Activations