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

    Neuronpedia

    INDEX
    Explanations

    if/then statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    双向
    -0.07
    CharacterSet
    -0.07
     facet
    -0.07
     unfit
    -0.07
    新农村
    -0.07
    VB
    -0.07
    UNIT
    -0.07
    尘
    -0.07
    四个
    -0.07
     bustling
    -0.07
    POSITIVE LOGITS
     conformity
    0.07
     paying
    0.07
    _plate
    0.07
    菩提
    0.07
     zie
    0.06
    😚
    0.06
     ako
    0.06
     Pepsi
    0.06
     brand
    0.06
     Paid
    0.06
    Act Density 0.131%

    No Known Activations