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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     singularity
    0.94
    료
    0.94
    infty
    0.89
     persistence
    0.86
     nigga
    0.86
     measuring
    0.86
    tive
    0.86
     leveraging
    0.84
    ي
    0.84
     originality
    0.83
    POSITIVE LOGITS
    ፈል
    0.96
     appellants
    0.91
    Clinical
    0.89
     जेब
    0.89
    joner
    0.87
     aider
    0.86
     appellant
    0.84
    Clin
    0.83
    ведений
    0.83
     गेल
    0.83
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.