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

    Neuronpedia

    INDEX
    Explanations

    statistics and quantification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aprende
    0.66
     aprendido
    0.65
     Arte
    0.63
     conserved
    0.63
    cort
    0.62
    igues
    0.61
     уроке
    0.60
     maximal
    0.60
     味
    0.60
    вли
    0.60
    POSITIVE LOGITS
     statistics
    2.33
     Statistics
    2.16
     statistic
    2.03
    Statistics
    1.96
    statistics
    1.91
     Statistic
    1.88
     chiffres
    1.86
     stats
    1.85
     numbers
    1.82
     statistik
    1.81
    Act Density 1.206%

    No Known Activations