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

    Neuronpedia

    INDEX
    Explanations

    atomic lattice structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nad
    0.39
     slug
    0.39
     streng
    0.37
    Objective
    0.37
     nad
    0.37
    絮
    0.37
    slug
    0.36
    Evidence
    0.36
     spect
    0.35
    scenario
    0.35
    POSITIVE LOGITS
     sublattice
    0.66
     atoms
    0.60
     الموقع
    0.58
     site
    0.57
    サイト
    0.56
     sitios
    0.55
     sites
    0.55
     SITE
    0.54
    網站
    0.54
     sitio
    0.52
    Act Density 0.016%

    No Known Activations