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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ↵↵
    0.74
    ار
    0.73
    d
    0.72
     T
    0.70
     pizza
    0.69
     tru
    0.69
    ar
    0.68
     He
    0.66
    9
    0.65
     l
    0.64
    POSITIVE LOGITS
    писок
    0.86
    ских
    0.82
    ষুধ
    0.78
     subclasses
    0.75
    τικών
    0.74
    ского
    0.73
    ങ്കിലും
    0.73
     subsidiaries
    0.72
     হাঁট
    0.72
    ゥム
    0.71
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.