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

    Neuronpedia

    INDEX
    Explanations

    sorting algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dequeue
    0.43
    Evolution
    0.39
    電視
    0.37
    俆
    0.37
     delegation
    0.36
    രീ
    0.35
    Dismiss
    0.34
    唐
    0.34
    পাত
    0.33
     במש
    0.33
    POSITIVE LOGITS
     upris
    0.48
     опор
    0.45
     anchor
    0.44
    key
    0.43
     hoger
    0.42
     начали
    0.41
     anchors
    0.40
    𒈹
    0.40
     distributor
    0.40
     tracer
    0.40
    Act Density 0.022%

    No Known Activations