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

    Neuronpedia

    INDEX
    Explanations

    ninth or nine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ７
    0.90
    7
    0.83
     Seven
    0.82
    ٧
    0.80
    ⁷
    0.79
     ১৯৭
    0.79
     fourteen
    0.78
     seven
    0.78
    0.76
     七
    0.76
    POSITIVE LOGITS
    ⑨
    0.79
    0.77
    0.70
                                
    0.68
                    
    0.68
     девя
    0.67
    ixe
    0.67
    第九
    0.67
    ixes
    0.66
     九
    0.65
    Act Density 0.026%

    No Known Activations