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

    Neuronpedia

    INDEX
    Explanations

    replication, field trials, samples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    合格
    0.47
     tested
    0.46
    Населення
    0.44
     population
    0.42
     qualified
    0.42
    人口
    0.41
    vider
    0.41
     seminal
    0.40
     populations
    0.40
    tested
    0.40
    POSITIVE LOGITS
     Replication
    0.84
     replicated
    0.82
     replication
    0.73
     replicate
    0.71
     Replica
    0.66
     replic
    0.66
     replicates
    0.64
    Layout
    0.61
     Plots
    0.61
     поле
    0.60
    Act Density 0.005%

    No Known Activations