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

    Neuronpedia

    INDEX
    Explanations

    programming language libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*;
    1.07
    ::
    0.84
    Бу
    0.78
     setToDefault
    0.78
    Latency
    0.76
    )$$
    0.76
    rVert
    0.76
    ::_
    0.75
    Futures
    0.75
    Просе
    0.74
    POSITIVE LOGITS
     English
    0.64
     parts
    0.58
     lj
    0.58
     Pä
    0.57
     vocal
    0.56
    인지
    0.55
     vært
    0.55
     kala
    0.55
     semi
    0.54
     people
    0.54
    Act Density 0.014%

    No Known Activations