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

    Neuronpedia

    INDEX
    Explanations

    here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lie
    0.56
     swelling
    0.49
     raised
    0.49
     m
    0.49
     Stories
    0.48
     Il
    0.47
      
    0.47
     Ön
    0.47
     Timeline
    0.47
     Refresh
    0.47
    POSITIVE LOGITS
    Here
    0.81
    here
    0.79
     here
    0.76
     aquí
    0.75
    在這裡
    0.73
     acá
    0.73
     aici
    0.72
    ```
    0.70
    mittedly
    0.68
    Yeah
    0.66
    Act Density 0.346%

    No Known Activations