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

    Neuronpedia

    INDEX
    Explanations

    dictionaries and import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     właśnie
    0.43
     요청
    0.43
     예정
    0.42
     aște
    0.42
     ketentuan
    0.41
     ulter
    0.40
     പ്രതീ
    0.40
     신
    0.39
     dispensation
    0.39
    واخر
    0.39
    POSITIVE LOGITS
    img
    0.49
    rank
    0.47
    length
    0.47
    item
    0.46
    C
    0.46
    DEBUG
    0.45
    0.44
    Q
    0.44
    table
    0.43
    paths
    0.43
    Act Density 0.008%

    No Known Activations