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

    Neuronpedia

    INDEX
    Explanations

    tell you much about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ುನ
    0.40
     करताना
    0.38
     necessidade
    0.36
     మంది
    0.36
    raison
    0.35
     تمامی
    0.35
     Gründe
    0.35
    បែ
    0.34
    綺
    0.34
    ताना
    0.34
    POSITIVE LOGITS
     nothing
    1.06
     NOTHING
    0.90
    nothing
    0.87
     Nothing
    0.87
     ничего
    0.84
    Nothing
    0.82
     much
    0.78
     something
    0.78
     little
    0.73
     многое
    0.72
    Act Density 0.009%

    No Known Activations