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

    Neuronpedia

    INDEX
    Explanations

    integrated information theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supervis
    0.39
     கிட்ட
    0.39
    喟
    0.38
     supervised
    0.38
     الحسن
    0.38
     Supervis
    0.38
     Migrate
    0.37
    出発
    0.37
    ับสนุน
    0.37
     නිෂ්
    0.37
    POSITIVE LOGITS
     entropy
    0.39
    intrinsic
    0.39
     exclusion
    0.39
     information
    0.38
     unpredict
    0.37
     uniqueness
    0.37
     equated
    0.37
     quantified
    0.36
     differentiated
    0.36
     intracranial
    0.36
    Act Density 0.008%

    No Known Activations