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

    Neuronpedia

    INDEX
    Explanations

    present value calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Observation
    0.43
     obliterated
    0.42
     hinzufügen
    0.42
     observación
    0.42
    nél
    0.41
     rappelle
    0.40
     esiste
    0.40
    分钟
    0.39
     scuola
    0.39
    iziert
    0.39
    POSITIVE LOGITS
     fiduciary
    0.41
     cashback
    0.41
     depreci
    0.40
    💸
    0.38
    пуск
    0.38
     financials
    0.37
    рее
    0.37
     мою
    0.37
     할인
    0.37
     পেনশন
    0.36
    Act Density 0.001%

    No Known Activations