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

    Neuronpedia

    INDEX
    Explanations

    enhances or improves function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    抱怨
    0.69
    失敗
    0.65
     monta
    0.65
    aphazard
    0.63
     неуда
    0.62
    ecuzione
    0.62
     backlash
    0.61
     perp
    0.60
     outlier
    0.60
     compi
    0.60
    POSITIVE LOGITS
     stimulates
    1.79
     improves
    1.79
     improve
    1.78
     stimulate
    1.76
     soothing
    1.70
     stimulating
    1.68
     revitalize
    1.68
     improving
    1.67
     boosts
    1.66
     boosting
    1.63
    Act Density 0.484%

    No Known Activations