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

    Neuronpedia

    INDEX
    Explanations

    concepts and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ümüz
    0.46
     اید
    0.45
    ⌀
    0.44
     الأولى
    0.44
     =)
    0.44
    regression
    0.44
    Isn
    0.43
     Saison
    0.43
    地區
    0.43
     δημιουργ
    0.43
    POSITIVE LOGITS
    л
    0.53
     nito
    0.52
    д
    0.51
    ко
    0.48
    션
    0.48
     fares
    0.47
     করে
    0.46
     cloth
    0.46
     parli
    0.45
    дав
    0.45
    Act Density 0.001%

    No Known Activations