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

    Neuronpedia

    INDEX
    Explanations

    Here's how to calculate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pee
    0.50
    ⌜
    0.50
     Aroma
    0.49
     Jer
    0.48
     Expect
    0.48
     expecting
    0.48
     Cast
    0.48
    賤
    0.48
    తలు
    0.47
     Qaeda
    0.47
    POSITIVE LOGITS
    calculation
    0.73
     calculation
    0.73
    longer
    0.71
    compound
    0.69
    calculator
    0.68
     inversión
    0.67
    calculations
    0.67
    Calculation
    0.67
    chart
    0.67
     exponential
    0.66
    Act Density 0.005%

    No Known Activations