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

    Neuronpedia

    INDEX
    Explanations

    national helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     с
    0.84
    的
    0.72
     نمی
    0.70
     jeg
    0.69
     this
    0.69
     with
    0.67
    рыв
    0.67
     явно
    0.66
     csak
    0.65
     wouldn
    0.65
    POSITIVE LOGITS
    PathDirectory
    0.89
    र्टी
    0.88
    เภท
    0.87
    িসি
    0.86
     Gemeinschaft
    0.86
     géographique
    0.85
    érrez
    0.83
     geographic
    0.83
     geografia
    0.83
    ڈی
    0.82
    Act Density 0.002%

    No Known Activations