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

    Neuronpedia

    INDEX
    Explanations

    completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PPtr
    0.39
    ρον
    0.37
    ड़े
    0.37
     plabic
    0.33
     күз
    0.33
    岐
    0.33
     لحد
    0.32
    ковый
    0.32
     pabbaj
    0.32
    lceil
    0.31
    POSITIVE LOGITS
     completion
    4.25
     completing
    3.97
     Completion
    3.95
    Completion
    3.89
    completion
    3.89
     completes
    3.81
     Comple
    3.81
    Comple
    3.80
     completed
    3.78
    完成
    3.69
    Act Density 0.192%

    No Known Activations