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

    Neuronpedia

    INDEX
    Explanations

    what needs to be found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hundreds
    0.85
    Hundreds
    0.84
     hamburgers
    0.84
     millions
    0.82
     Hundreds
    0.82
     billions
    0.81
    ummies
    0.79
     engravings
    0.79
     millones
    0.78
     cheeses
    0.77
    POSITIVE LOGITS
    Missing
    1.10
     missing
    1.04
     Missing
    0.98
    missing
    0.96
    缺失
    0.96
     लापता
    0.79
     hilang
    0.74
     cũng
    0.73
     solve
    0.72
     fehlt
    0.70
    Act Density 0.010%

    No Known Activations