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

    Neuronpedia

    INDEX
    Explanations

    p

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hänen
    0.96
    ientôt
    0.86
     tätig
    0.85
     his
    0.84
     아버지
    0.83
     reboot
    0.82
    เธอ
    0.82
     blacksmith
    0.81
     hago
    0.80
     errands
    0.80
    POSITIVE LOGITS
     statistically
    1.54
     statistical
    1.52
    statistical
    1.33
     статисти
    1.29
    Statistical
    1.23
     statistic
    1.19
     quantile
    1.18
     overfitting
    1.18
     Statistical
    1.16
     covariates
    1.16
    Act Density 0.014%

    No Known Activations