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

    Neuronpedia

    INDEX
    Explanations

    seed and rank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diameter
    0.75
    limsup
    0.67
    diameter
    0.66
     თ
    0.66
    counts
    0.65
     Diameter
    0.65
    ชน
    0.65
    select
    0.63
     നിര
    0.63
    triangle
    0.62
    POSITIVE LOGITS
     seeds
    1.59
     seed
    1.57
     seeded
    1.45
     ranked
    1.38
     Seed
    1.37
     rankings
    1.33
    seeds
    1.33
    Seeds
    1.33
     Seeds
    1.33
     seeding
    1.31
    Act Density 0.083%

    No Known Activations