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

    Neuronpedia

    INDEX
    Explanations

    argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    حفاظ
    -0.07
    赐
    -0.07
    ,j
    -0.07
    _event
    -0.07
    �建
    -0.07
    伙伴
    -0.07
    .DrawLine
    -0.06
    眺
    -0.06
    睑
    -0.06
    :e
    -0.06
    POSITIVE LOGITS
     a
    0.07
    -master
    0.07
     multer
    0.07
     Hindi
    0.07
    A
    0.07
     brisk
    0.06
     méthode
    0.06
     graphs
    0.06
     smoked
    0.06
    GBK
    0.06
    Act Density 0.015%

    No Known Activations