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

    Neuronpedia

    INDEX
    Explanations

    mathematical group theory concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chocolate
    0.37
    intro
    0.36
     adaptés
    0.36
    模
    0.36
    backend
    0.36
    を超
    0.36
    ILLA
    0.36
    roffenen
    0.35
    针对
    0.35
    社会主义
    0.35
    POSITIVE LOGITS
     subgroup
    0.68
     Generators
    0.66
     generators
    0.64
     generator
    0.63
     Generator
    0.57
    generators
    0.57
     order
    0.55
     degree
    0.52
     generating
    0.50
     Generated
    0.50
    Act Density 0.006%

    No Known Activations