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

    Neuronpedia

    INDEX
    Explanations

    list items or headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #,
    0.38
    ®,
    0.37
    ,
    0.36
    prisingly
    0.36
    !,
    0.35
    ...,
    0.34
    laşt
    0.34
    *,
    0.34
    --,
    0.33
    …。
    0.33
    POSITIVE LOGITS
    whatever
    0.55
     whatever
    0.50
     whichever
    0.47
     Whatever
    0.46
    Whatever
    0.44
    ش
    0.44
     등의
    0.41
     등으로
    0.40
     equivalent
    0.40
     போன்றவற்ற
    0.40
    Act Density 0.072%

    No Known Activations