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

    Neuronpedia

    INDEX
    Explanations

    Solar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    de
    2.06
    ara
    1.98
    om
    1.68
    ist
    1.68
    benar
    1.64
    gi
    1.61
    gg
    1.59
    inin
    1.59
    ありません
    1.59
    من
    1.59
    POSITIVE LOGITS
     loudness
    1.48
    지
    1.35
    నే
    1.28
    覧
    1.26
     kuid
    1.24
     gradation
    1.23
    ");
    1.22
     gui
    1.22
     usher
    1.22
    心思
    1.21
    Act Density 0.233%

    No Known Activations