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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    कारा
    0.89
    दयाल
    0.88
    elope
    0.84
    ilus
    0.81
    ъ
    0.79
    zing
    0.78
     badi
    0.77
    adang
    0.75
    agonia
    0.75
    ೈನ್
    0.75
    POSITIVE LOGITS
     Ministry
    0.84
     civ
    0.84
     Topics
    0.83
     Rector
    0.83
    MATERIALS
    0.81
     Gates
    0.80
     Citizenship
    0.80
    يئة
    0.80
    拿
    0.79
    VAE
    0.78
    Act Density 0.000%

    No Known Activations