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

    Neuronpedia

    INDEX
    Explanations

    environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쿠
    -0.07
     HEX
    -0.07
    _Menu
    -0.07
     Reed
    -0.06
     نیم
    -0.06
    ure
    -0.06
    _st
    -0.06
     زوج
    -0.06
    701
    -0.06
    .TRA
    -0.06
    POSITIVE LOGITS
     lbs
    0.07
    Khi
    0.06
    ickým
    0.06
     Sho
    0.06
    (Equal
    0.06
     čty
    0.06
    Less
    0.06
    _ALARM
    0.06
     Somehow
    0.06
     Jaguars
    0.06
    Act Density 0.012%

    No Known Activations