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

    Neuronpedia

    INDEX
    Explanations

    narrative and storytelling structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    प्तान
    0.41
     hre
    0.39
    po
    0.37
     révèle
    0.37
    বিশ্ব
    0.36
     commandant
    0.36
    ια
    0.36
    ține
    0.36
    ním
    0.35
     asso
    0.35
    POSITIVE LOGITS
     جمله
    0.43
     rite
    0.38
     nettement
    0.37
     STEM
    0.37
     tending
    0.37
     جذاب
    0.36
    眇
    0.36
     нет
    0.35
    によって
    0.34
     }}^{\
    0.34
    Act Density 0.003%

    No Known Activations