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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    juven
    0.78
    elves
    0.77
    dess
    0.74
    fø
    0.73
    від
    0.72
    𝖾
    0.71
     CDB
    0.71
    clerosis
    0.70
    ȩ
    0.70
    lé
    0.70
    POSITIVE LOGITS
     Priorities
    0.79
     priorities
    0.79
     Dish
    0.78
     Tage
    0.77
     Polen
    0.76
     Forschung
    0.75
     count
    0.75
     Tenure
    0.73
     somma
    0.73
     ț
    0.73
    Act Density 0.000%

    No Known Activations