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

    Neuronpedia

    INDEX
    Explanations

    understand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    encers
    -0.07
     أحمد
    -0.07
     dir
    -0.07
    иб
    -0.06
     corro
    -0.06
    宋体
    -0.06
    꾸
    -0.06
    �
    -0.06
     thủy
    -0.06
    ffi
    -0.06
    POSITIVE LOGITS
     supplement
    0.07
    ationale
    0.07
    _before
    0.06
    otype
    0.06
     gele
    0.06
    code
    0.06
    videos
    0.06
    zá
    0.06
    으나
    0.06
     Jan
    0.06
    Act Density 0.023%

    No Known Activations