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

    Neuronpedia

    INDEX
    Explanations

    Supreme Court cases and judgements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Scales
    0.52
     scales
    0.44
    courts
    0.43
    scales
    0.41
     courts
    0.40
     Percol
    0.39
     Greg
    0.39
     न्यायालय
    0.37
     আদালত
    0.37
     extrem
    0.37
    POSITIVE LOGITS
     Museum
    0.43
     ऑफ
    0.41
     ഓഫ്
    0.41
     komplex
    0.40
     activism
    0.40
     digitization
    0.39
    rue
    0.38
    缟
    0.38
     gardener
    0.37
     mania
    0.37
    Act Density 0.004%

    No Known Activations