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

    Neuronpedia

    INDEX
    Explanations

    religion and politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    妮
    -0.06
     Russian
    -0.06
     notation
    -0.06
    _customer
    -0.06
     πα
    -0.06
    čku
    -0.06
     leaving
    -0.06
    における
    -0.06
     А
    -0.06
    045
    -0.05
    POSITIVE LOGITS
     Ages
    0.07
     ages
    0.06
     Bust
    0.06
     -------↵
    0.06
    -warning
    0.06
    )();↵
    0.06
     diagon
    0.06
     rant
    0.06
     Ban
    0.06
     Stellar
    0.06
    Act Density 0.093%

    No Known Activations