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

    Neuronpedia

    INDEX
    Explanations

    retrieval and routing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    processes
    0.74
     श्रमिक
    0.74
    Processes
    0.72
     Processes
    0.70
    Tasks
    0.68
     labors
    0.66
     processes
    0.65
    bor
    0.63
    diox
    0.62
     विज्ञ
    0.60
    POSITIVE LOGITS
    检索
    0.81
    ದಲು
    0.80
    חי
    0.74
     serve
    0.74
     دیک
    0.73
    ヒット
    0.72
     serves
    0.71
    Lookup
    0.69
     retrieval
    0.69
     served
    0.69
    Act Density 0.186%

    No Known Activations