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

    Neuronpedia

    INDEX
    Explanations

    `using UnityEngine` code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Baseline
    0.79
     Mey
    0.71
    Targets
    0.69
     vegetarians
    0.68
     ডকুমেন্ট
    0.68
    ppins
    0.68
    ప్పటి
    0.67
    ayscale
    0.67
    zwe
    0.66
    Tropical
    0.66
    POSITIVE LOGITS
     било
    0.85
    ஷி
    0.79
     ইহা
    0.77
     له
    0.74
     कुनै
    0.74
     enquiries
    0.72
     আর্মি
    0.71
     ('
    0.69
    தோ
    0.68
     இரா
    0.68
    Act Density 0.008%

    No Known Activations