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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .acquire
    -0.07
    Trivia
    -0.07
     observers
    -0.07
     seguro
    -0.07
    外汇
    -0.07
    冶炼
    -0.07
     INV
    -0.06
     treasury
    -0.06
     upside
    -0.06
     vér
    -0.06
    POSITIVE LOGITS
     dynam
    0.07
    恶
    0.07
    åde
    0.07
    镇
    0.07
     IDisposable
    0.07
     func
    0.07
    .FileReader
    0.06
     configuring
    0.06
    мож
    0.06
    _recipe
    0.06
    Act Density 0.032%

    No Known Activations