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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by )

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "]).
    1.03
    "],
    1.01
    "];
    1.01
    "]),
    0.98
    '],
    0.96
    '];
    0.96
     We
    0.95
     we
    0.93
    "].
    0.92
    "])
    0.92
    POSITIVE LOGITS
    )(
    0.93
     ちゃん
    0.81
    )(((
    0.77
     هغه
    0.75
    )’
    0.75
    )((
    0.74
    )(\
    0.73
     уравнение
    0.73
     kanyang
    0.72
    辦法
    0.72
    Act Density 0.638%

    No Known Activations