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

    Neuronpedia

    INDEX
    Explanations

    Object

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    更加
    -0.07
    .it
    -0.07
    ":[
    -0.07
     hint
    -0.07
    عكس
    -0.07
     “[
    -0.07
     animated
    -0.07
     int
    -0.07
    吐槽
    -0.07
    "[
    -0.06
    POSITIVE LOGITS
     Hobby
    0.08
    健康产业
    0.08
     Physiology
    0.08
    抗体
    0.08
     lowest
    0.07
     pathlib
    0.07
     '').
    0.07
    变速
    0.07
    _Last
    0.07
    _thickness
    0.07
    Act Density 0.002%

    No Known Activations