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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ropes
    1.05
     automorphism
    0.94
     backstory
    0.88
    atorics
    0.82
     begrenzt
    0.82
     objectifs
    0.81
     Schematic
    0.81
     Monetary
    0.80
     hypotheses
    0.80
    脲
    0.79
    POSITIVE LOGITS
    m
    0.99
    ný
    0.92
    ن
    0.92
     મુજબ
    0.90
    nad
    0.90
    mä
    0.89
    ných
    0.88
    ned
    0.86
    nin
    0.85
    nie
    0.85
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.