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

    Neuronpedia

    INDEX
    Explanations

    botanically or actually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supremac
    0.45
    менова
    0.44
     aument
    0.43
     dwellers
    0.43
     conject
    0.43
     exorbit
    0.43
     dever
    0.42
    winds
    0.42
     superstitious
    0.42
    wind
    0.41
    POSITIVE LOGITS
    धरी
    0.43
     एल
    0.42
    ूती
    0.42
     टीवी
    0.41
    驹
    0.40
    样
    0.40
    량이
    0.39
    样品
    0.39
    ка
    0.39
    িনি
    0.38
    Act Density 0.001%

    No Known Activations