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

    Neuronpedia

    INDEX
    Explanations

    mathematical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    우리
    -0.07
     Του
    -0.06
     Ups
    -0.06
    KI
    -0.06
     آب
    -0.06
    'We
    -0.06
     DHS
    -0.06
     Chennai
    -0.06
     Gan
    -0.06
     Gn
    -0.06
    POSITIVE LOGITS
     mathematical
    0.07
    _MAT
    0.07
    query
    0.06
    PX
    0.06
    (features
    0.06
    мат
    0.06
     데이터
    0.06
    σκευ
    0.06
    阅
    0.06
     Exact
    0.06
    Act Density 0.012%

    No Known Activations