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

    Neuronpedia

    INDEX
    Explanations

    7 and Exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vector
    0.74
     htim
    0.69
    itional
    0.69
     DMD
    0.68
     Salam
    0.67
     Dam
    0.66
     salinity
    0.66
     Salamanca
    0.65
     vettore
    0.65
     Hirsch
    0.64
    POSITIVE LOGITS
     površ
    0.56
     কাহ
    0.53
    кновен
    0.51
     நோக்க
    0.51
     sınır
    0.48
     उपास
    0.48
     مختصر
    0.47
     greater
    0.47
     разработки
    0.46
     merging
    0.46
    Act Density 0.175%

    No Known Activations