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

    Neuronpedia

    INDEX
    Explanations

    code and math snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tjiwarl
    0.33
    ുപത്രി
    0.32
    щён
    0.31
    ették
    0.29
    BLEND
    0.29
    <unused40>
    0.29
     parochial
    0.29
    uspended
    0.29
    asyarakat
    0.27
    嶄
    0.27
    POSITIVE LOGITS
    x
    0.32
     i
    0.32
    s
    0.30
    0
    0.29
     )
    0.29
    n
    0.29
     ve
    0.29
     ,
    0.29
    ve
    0.28
    y
    0.28
    Act Density 0.178%

    No Known Activations