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

    Neuronpedia

    INDEX
    Explanations

    imported as a module

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AssignableFrom
    0.68
     popol
    0.64
     Ill
    0.63
     System
    0.62
     Source
    0.62
     Solve
    0.61
     popular
    0.61
     Drive
    0.61
     or
    0.61
     license
    0.59
    POSITIVE LOGITS
     chlorides
    0.94
     cuyos
    0.92
    🔘
    0.92
     राज्य
    0.91
     qubits
    0.91
     ombil
    0.90
     высо
    0.90
     alkaloids
    0.89
     accuracies
    0.88
    .'),
    0.87
    Act Density 0.023%

    No Known Activations