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

    Neuronpedia

    INDEX
    Explanations

    kit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    علي
    -0.09
    cedes
    -0.08
     Inline
    -0.07
     رقم
    -0.07
    عزي
    -0.07
    ある
    -0.07
    remove
    -0.07
    semicolon
    -0.07
    Diese
    -0.07
     And
    -0.07
    POSITIVE LOGITS
     Arrange
    0.08
    ,Z
    0.07
     collections
    0.07
    _inventory
    0.07
    _pot
    0.07
     Penguin
    0.07
    /examples
    0.07
    Font
    0.07
     started
    0.07
     fisheries
    0.06
    Act Density 0.002%

    No Known Activations