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

    Neuronpedia

    INDEX
    Explanations

    public class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     main
    0.98
    main
    0.89
    Main
    0.74
     Main
    0.73
     MAIN
    0.69
    MAIN
    0.67
    主
    0.63
     mainu
    0.62
     მთავ
    0.60
     اصلی
    0.59
    POSITIVE LOGITS
    <unused89>
    0.43
    CRM
    0.40
    owskiego
    0.40
    gladbach
    0.39
    epte
    0.37
    യ്ക്ക്
    0.36
    യ്
    0.36
    公
    0.36
     灯
    0.36
    esimo
    0.36
    Act Density 0.000%

    No Known Activations