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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     jeweiligen
    0.51
     каждого
    0.43
     masing
    0.41
     jeweil
    0.41
    став
    0.38
    ুণ
    0.37
    ஶ
    0.37
     respective
    0.36
     rushes
    0.36
    ङ
    0.36
    POSITIVE LOGITS
    doctoral
    0.39
    FBS
    0.38
     FBS
    0.38
     CID
    0.38
    സൈ
    0.38
    変数
    0.38
     PhD
    0.37
    scala
    0.37
     OCD
    0.37
    🧬
    0.37
    Act Density 0.000%

    No Known Activations