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

    Neuronpedia

    INDEX
    Explanations

    persistent homology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कार्
    0.38
    捩
    0.38
     অর্চন
    0.37
    cepteur
    0.36
    obank
    0.36
     жак
    0.35
    鹏
    0.35
     Yellow
    0.35
     attenu
    0.35
    குதி
    0.35
    POSITIVE LOGITS
     homology
    0.66
     chain
    0.50
     persistence
    0.50
    Chain
    0.47
     Chain
    0.46
     persists
    0.45
     persist
    0.44
     Persistent
    0.44
     persistent
    0.44
     chains
    0.44
    Act Density 0.008%

    No Known Activations