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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.62
     k
    0.47
     kyr
    0.45
     pd
    0.45
    n
    0.44
     cs
    0.43
    x
    0.43
     kut
    0.43
     km
    0.42
     έ
    0.42
    POSITIVE LOGITS
    Tabpage
    0.48
    спомина
    0.47
     ወይም
    0.45
     Bhagava
    0.45
    Traversal
    0.44
    Subgraph
    0.43
    0.43
    嗶
    0.42
     aplatis
    0.42
    pInBuffer
    0.42
    Act Density 0.030%

    No Known Activations