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

    Neuronpedia

    INDEX
    Explanations

    code constructs with data operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pending
    0.50
    𒂵
    0.50
    应用程序
    0.49
     TNumber
    0.49
    Decimal
    0.49
     समाचार
    0.48
    Documentation
    0.48
    Cancellation
    0.48
    ายเป็น
    0.48
    FileInputExcel
    0.47
    POSITIVE LOGITS
     baseline
    0.84
     results
    0.75
    baseline
    0.72
     trajectories
    0.70
     spectra
    0.64
     final
    0.64
     combined
    0.63
     posterior
    0.62
    avg
    0.61
     ensemble
    0.61
    Act Density 0.004%

    No Known Activations