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

    Neuronpedia

    INDEX
    Explanations

    programming keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dessert
    -0.07
     dakika
    -0.06
     notify
    -0.06
     đỡ
    -0.06
     incarceration
    -0.06
     debates
    -0.06
    덕
    -0.06
     mayo
    -0.06
    odings
    -0.06
     UserDao
    -0.06
    POSITIVE LOGITS
    _COLUMN
    0.07
    :D
    0.06
    ์ของ
    0.06
    音乐
    0.06
    ыва
    0.06
     Guid
    0.06
     '",
    0.06
     Gael
    0.06
    ',"
    0.06
    ağa
    0.06
    Act Density 0.088%

    No Known Activations