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

    Neuronpedia

    INDEX
    Explanations

    Internal Audit, angry, pip, Reaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     എല്ലാ
    0.44
     ವಿಧಾನಸಭಾ
    0.43
     отмеча
    0.42
     HashSet
    0.41
     detall
    0.40
     ആവശ്യ
    0.40
     وم
    0.39
     ವಿಧಾನಸ
    0.39
     اکاؤنٹ
    0.39
     Ev
    0.39
    POSITIVE LOGITS
    it
    0.45
    anos
    0.45
     Repair
    0.45
    fica
    0.45
    itif
    0.44
    bridal
    0.44
    ায়
    0.43
    য়নে
    0.42
    iyaki
    0.42
    amac
    0.42
    Act Density 0.002%

    No Known Activations