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

    Neuronpedia

    INDEX
    Explanations

    System.out.println

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supervision
    0.70
     moored
    0.65
     pending
    0.65
     supervisory
    0.64
     collation
    0.62
     정의역
    0.61
     slit
    0.61
     unsupervised
    0.61
     volunteered
    0.61
     returned
    0.61
    POSITIVE LOGITS
    System
    2.57
     System
    2.32
    Syst
    1.76
     sistema
    1.61
     система
    1.61
     systemu
    1.60
     Syst
    1.58
    システム
    1.57
    system
    1.56
    Systems
    1.53
    Act Density 0.245%

    No Known Activations