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

    Neuronpedia

    INDEX
    Explanations

    integration and emergence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लंबाई
    0.36
    մ
    0.35
     पुरानी
    0.35
     столи
    0.35
    GREES
    0.35
     rumour
    0.34
    йт
    0.34
     Mafia
    0.34
     Latin
    0.34
     उंची
    0.34
    POSITIVE LOGITS
     integration
    0.43
     aggregation
    0.42
    梱
    0.41
     integração
    0.41
    loops
    0.40
     loops
    0.39
    هاز
    0.39
     solidification
    0.39
     integrate
    0.38
     integrative
    0.38
    Act Density 0.000%

    No Known Activations