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

    Neuronpedia

    INDEX
    Explanations

    stages, steps, or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    émie
    0.65
     Discounts
    0.60
    蒻
    0.59
     মারা
    0.58
    emies
    0.58
     限
    0.58
     sparsity
    0.57
    cropped
    0.57
    ับสนุน
    0.56
     formatter
    0.56
    POSITIVE LOGITS
     process
    2.51
     processo
    2.50
    Process
    2.48
     proceso
    2.41
     processus
    2.36
     Process
    2.36
    process
    2.35
     processes
    2.28
     steps
    2.27
    过程
    2.22
    Act Density 1.980%

    No Known Activations