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

    Neuronpedia

    INDEX
    Explanations

    Information/Propaganda

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    愛情
    -0.07
     Cooperation
    -0.07
    閱讀
    -0.07
    ("="
    -0.07
     giov
    -0.07
    adelphia
    -0.06
     docking
    -0.06
     EVE
    -0.06
     reference
    -0.06
     joint
    -0.06
    POSITIVE LOGITS
    тики
    0.07
     Tooltip
    0.07
    שות
    0.07
    olarity
    0.07
    boxes
    0.07
     terrified
    0.07
    살
    0.07
    前几年
    0.07
    قيم
    0.07
    exec
    0.07
    Act Density 0.005%

    No Known Activations