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

    Neuronpedia

    INDEX
    Explanations

    resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beforeDir
    0.39
     Ernest
    0.38
    梅
    0.37
    ক্ষা
    0.35
     Lug
    0.35
    ង់
    0.34
    ిత
    0.34
     lãi
    0.34
     mediana
    0.34
     tronco
    0.34
    POSITIVE LOGITS
     resources
    4.47
    资源
    4.34
     resource
    4.13
    資源
    4.13
    resources
    4.06
     recursos
    4.03
     Resources
    3.94
     ресур
    3.94
    Resources
    3.88
     risorse
    3.86
    Act Density 0.274%

    No Known Activations