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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isodes
    1.12
    Transformers
    1.10
     Transformers
    1.09
     CHEMISTRY
    1.07
     Bethel
    1.06
     spacers
    1.04
     Carth
    1.02
    Thor
    1.02
    BTC
    1.02
     iPads
    1.02
    POSITIVE LOGITS
    ū
    0.93
    ují
    0.90
     następ
    0.90
    úd
    0.86
    på
    0.86
     fyra
    0.86
     ছয়
    0.83
     gär
    0.83
     négy
    0.82
     hãy
    0.82
    Act Density 0.000%

    No Known Activations