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

    Neuronpedia

    INDEX
    Explanations

    rugby positions and teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idin
    -0.71
    cology
    -0.68
    relser
    -0.67
     listas
    -0.66
     ח
    -0.66
    erie
    -0.66
     }}$.
    -0.65
     Ouest
    -0.65
     ),
    -0.65
    )‏
    -0.65
    POSITIVE LOGITS
     halves
    1.01
     fly
    0.98
    half
    0.91
     unsalted
    0.90
     HALF
    0.85
    Half
    0.85
     Half
    0.83
     half
    0.81
     despatched
    0.81
    HALF
    0.79
    Act Density 0.013%

    No Known Activations