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

    Neuronpedia

    INDEX
    Explanations

    why my bill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সত্যিকার
    0.46
     doomed
    0.42
     mucho
    0.41
     آمریکا
    0.40
     controvers
    0.40
     awkwardly
    0.40
     европей
    0.39
    жется
    0.39
     scrollBody
    0.39
     नाट
    0.39
    POSITIVE LOGITS
     Hence
    0.72
    Hence
    0.72
     Gandhiji
    0.72
     till
    0.70
     Bhai
    0.69
     Apart
    0.68
     Indian
    0.68
     Telangana
    0.67
    till
    0.67
     Ganga
    0.66
    Act Density 0.002%

    No Known Activations