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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LOGIN
    -0.08
     Gibraltar
    -0.07
    ["_
    -0.06
    igned
    -0.06
     credibility
    -0.06
    信誉
    -0.06
    _available
    -0.06
    Reader
    -0.06
     Unexpected
    -0.06
    用心
    -0.06
    POSITIVE LOGITS
     cafe
    0.09
    أنواع
    0.07
    〔
    0.07
     ################################################################
    0.07
    chron
    0.07
    植物
    0.07
    Crit
    0.06
     svenska
    0.06
     Floral
    0.06
    trip
    0.06
    Act Density 0.002%

    No Known Activations