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

    Neuronpedia

    INDEX
    Explanations

    measuring or estimating based on data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٹرول
    0.69
     Découvrez
    0.66
     bénéf
    0.65
    Tune
    0.63
     invincible
    0.63
    endorong
    0.63
     സാധ്യത
    0.62
     Entities
    0.62
     ಅಪಾಯ
    0.62
    tune
    0.62
    POSITIVE LOGITS
     measurements
    2.48
     Measurements
    2.06
     measurement
    2.06
     measured
    1.96
    Measurements
    1.94
     measuring
    1.87
     observations
    1.81
    measure
    1.79
    measured
    1.76
     Measurement
    1.76
    Act Density 0.188%

    No Known Activations