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

    Neuronpedia

    INDEX
    Explanations

    introduction and topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     behest
    0.50
     restaurantes
    0.46
     warships
    0.45
    ोच्च
    0.45
    icação
    0.44
     restaurante
    0.43
     लाभार्थियों
    0.43
     বলেছে
    0.41
     барои
    0.41
     Jehova
    0.41
    POSITIVE LOGITS
     topics
    0.65
     Topics
    0.62
     Introduction
    0.60
     lectures
    0.58
    Topics
    0.58
     exploring
    0.57
     lecture
    0.57
     explore
    0.55
     explores
    0.54
     introductory
    0.54
    Act Density 0.052%

    No Known Activations