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

    Neuronpedia

    INDEX
    Explanations

    Multilingual concept recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.52
     war
    0.51
    7
    0.50
    _
    0.49
    ```
    0.46
    1
    0.46
    6
    0.45
     elastic
    0.45
     protobuf
    0.44
    8
    0.44
    POSITIVE LOGITS
     condizioni
    0.39
     ハイ
    0.39
    insieme
    0.39
    ennem
    0.38
    性質
    0.38
    upra
    0.38
     פאר
    0.38
     അഗ്
    0.38
     ಸಮ
    0.38
     κατα
    0.38
    Act Density 0.001%

    No Known Activations