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

    Neuronpedia

    INDEX
    Explanations

    deeper into relaxation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.48
     M
    0.44
     Inhibition
    0.41
     [
    0.41
     hai
    0.40
     Aquare
    0.40
     É
    0.39
     cities
    0.39
     Han
    0.39
     i
    0.39
    POSITIVE LOGITS
    <unused2024>
    0.45
    <unused973>
    0.45
     максимально
    0.45
    <unused1864>
    0.44
    ༧
    0.44
    <unused1726>
    0.44
    <unused743>
    0.43
    ੌਰ
    0.43
    <unused275>
    0.43
    <unused558>
    0.42
    Act Density 0.002%

    No Known Activations