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

    Neuronpedia

    INDEX
    Explanations

    column

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .userData
    -0.08
    sent
    -0.07
     xmin
    -0.06
    บำ
    -0.06
    exists
    -0.06
    similar
    -0.06
    -headed
    -0.06
    GT
    -0.06
     flav
    -0.06
    ")),↵
    -0.06
    POSITIVE LOGITS
    remarks
    0.07
    ollections
    0.07
     awe
    0.07
    图书馆
    0.07
    SuppressLint
    0.07
    \Bridge
    0.07
     Bakery
    0.06
    踏
    0.06
     Brewery
    0.06
     chance
    0.06
    Act Density 0.038%

    No Known Activations