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

    Neuronpedia

    INDEX
    Explanations

    speed and efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    0.44
    6
    0.44
    9
    0.42
    5
    0.42
    0
    0.41
    take
    0.40
    3
    0.40
     estándar
    0.40
    7
    0.39
    োজনের
    0.38
    POSITIVE LOGITS
    िणी
    0.54
     現
    0.49
     `"
    0.49
     እንዲ
    0.45
     Associ
    0.44
     Lane
    0.43
     Vene
    0.43
     Tokens
    0.43
     Milan
    0.42
     Employees
    0.42
    Act Density 0.007%

    No Known Activations