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

    Neuronpedia

    INDEX
    Explanations

    double

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.70
     as
    0.62
    %)
    0.54
    ט
    0.54
     chủ
    0.52
     principais
    0.51
    }'
    0.50
     estable
    0.50
    }));
    0.49
     أس
    0.49
    POSITIVE LOGITS
     Double
    1.18
     double
    1.14
     डबल
    1.03
    Double
    1.02
     ダブル
    0.98
    双
    0.96
    double
    0.89
     doble
    0.84
     doppia
    0.84
     doppio
    0.84
    Act Density 0.021%

    No Known Activations