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

    Neuronpedia

    INDEX
    Explanations

    HTML structure elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //});
    -0.90
    })));
    -0.82
    さな
    -0.81
    擂
    -0.79
     Ս
    -0.77
     Կ
    -0.75
     potreb
    -0.74
     urbanas
    -0.74
    訛
    -0.74
    COA
    -0.73
    POSITIVE LOGITS
    br
    0.99
     boeken
    0.97
     MASON
    0.90
     memorized
    0.89
     résumé
    0.84
     maceta
    0.84
    zeera
    0.83
    誡
    0.82
     épisode
    0.82
    )　
    0.82
    Act Density 0.008%

    No Known Activations