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

    Neuronpedia

    INDEX
    Explanations

    comprehensive guide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elaborate
    0.42
    elabor
    0.41
    abstract
    0.40
    concept
    0.40
     concept
    0.40
     hypothesis
    0.40
     hypotheses
    0.40
    hypothesis
    0.40
    รายละเอียด
    0.39
    Definition
    0.39
    POSITIVE LOGITS
     guide
    1.41
     Guide
    1.20
    Guide
    1.19
    指南
    1.18
    guide
    1.15
     guides
    1.11
     guidebook
    1.05
     GUIDE
    1.04
     guía
    1.02
     गाइड
    1.02
    Act Density 0.072%

    No Known Activations