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

    Neuronpedia

    INDEX
    Explanations

    terrorist attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desa
    2.19
    Punjab
    1.93
    
    1.92
    featured
    1.90
     featured
    1.88
     ggplot
    1.79
    ہور
    1.77
    vì
    1.77
     tentatively
    1.76
     Eurovision
    1.71
    POSITIVE LOGITS
    繹
    2.25
    uminescence
    2.05
    RI
    1.98
    のが
    1.91
    ح
    1.90
    加えて
    1.89
     esterni
    1.87
     znacz
    1.85
    啷
    1.83
     اڈوں
    1.83
    Act Density 0.023%

    No Known Activations