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

    Neuronpedia

    INDEX
    Explanations

    more welcoming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    இரு
    0.45
    罾
    0.44
    ളെ
    0.43
    AddItem
    0.42
    )_{(
    0.39
    নর
    0.38
    赭
    0.38
    следования
    0.38
     Liza
    0.38
     प्रथा
    0.38
    POSITIVE LOGITS
     units
    0.46
     counts
    0.41
     weaker
    0.41
     count
    0.40
     instruments
    0.40
     delayed
    0.40
     mâ
    0.40
     —
    0.39
     junctions
    0.39
    PK
    0.39
    Act Density 0.001%

    No Known Activations