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

    Neuronpedia

    INDEX
    Explanations

    obtain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Sh
    -0.07
     Chatt
    -0.07
     bearings
    -0.06
     worthless
    -0.06
    Usage
    -0.06
    _yaw
    -0.06
     Jae
    -0.06
     Sant
    -0.06
    .bc
    -0.06
     Trying
    -0.06
    POSITIVE LOGITS
    leyici
    0.08
    {↵↵
    0.08
    android
    0.07
    (){↵
    0.07
    ":{↵
    0.07
    同时
    0.07
     sca
    0.07
     coquine
    0.07
    GPC
    0.06
     _______,
    0.06
    Act Density 0.001%

    No Known Activations