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

    Neuronpedia

    INDEX
    Explanations

    payment

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viewDidLoad
    0.41
     sit
    0.38
     markup
    0.38
     signs
    0.37
    evolving
    0.36
     embed
    0.35
     colonization
    0.35
     expression
    0.35
     votes
    0.34
     realization
    0.34
    POSITIVE LOGITS
    pay
    0.50
     PAY
    0.48
     Pay
    0.45
    pada
    0.44
     pay
    0.44
    客
    0.43
    val
    0.43
     night
    0.42
     शिप
    0.41
    火车
    0.41
    Act Density 0.001%

    No Known Activations