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

    Neuronpedia

    INDEX
    Explanations

    Continuous integration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الصادر
    -0.07
    Sure
    -0.07
     resolutions
    -0.07
    〘
    -0.07
    .var
    -0.06
     copyright
    -0.06
     портал
    -0.06
     hạ
    -0.06
     incurred
    -0.06
     touted
    -0.06
    POSITIVE LOGITS
    замен
    0.07
    科比
    0.07
    鲫
    0.07
    -Mart
    0.07
    .endTime
    0.07
    洗脸
    0.07
    _rhs
    0.07
     OnePlus
    0.07
    🐟
    0.07
    꼈
    0.07
    Act Density 0.026%

    No Known Activations