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

    Neuronpedia

    INDEX
    Explanations

    individual items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simplicity
    0.41
    匹
    0.39
     embodies
    0.39
     whats
    0.38
     wants
    0.38
     easy
    0.37
     his
    0.36
     সাজ
    0.36
     calmness
    0.36
     calm
    0.35
    POSITIVE LOGITS
     individually
    0.43
     इंफॉर्मेशन
    0.43
     प्लांट्स
    0.43
     Individ
    0.42
    individ
    0.42
    ￭
    0.42
    urten
    0.41
    ocket
    0.41
    Installed
    0.41
     indywidual
    0.41
    Act Density 0.003%

    No Known Activations