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

    Neuronpedia

    INDEX
    Explanations

    saying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Binder
    -0.07
    udas
    -0.07
    /shared
    -0.07
    _topic
    -0.07
    endi
    -0.06
    (factor
    -0.06
    Schema
    -0.06
     KDE
    -0.06
    UDO
    -0.06
     norm
    -0.06
    POSITIVE LOGITS
    γέν
    0.07
    Пер
    0.06
     installment
    0.06
     licence
    0.06
    _'+
    0.06
     Πέ
    0.06
    몰
    0.06
     assail
    0.05
     등의
    0.05
    .’
    0.05
    Act Density 0.109%

    No Known Activations