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

    Neuronpedia

    INDEX
    Explanations

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "=",
    -0.07
    전히
    -0.07
     silicon
    -0.06
    ataset
    -0.06
     rozhodnutí
    -0.06
    ниця
    -0.06
     ips
    -0.06
     متحده
    -0.06
     trhu
    -0.06
     حضور
    -0.06
    POSITIVE LOGITS
    .gson
    0.07
    购
    0.07
    Ui
    0.07
    ment
    0.06
    aged
    0.06
     targetType
    0.06
     Smoking
    0.06
    emony
    0.06
     Од
    0.06
    Craft
    0.06
    Act Density 0.005%

    No Known Activations