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

    Neuronpedia

    INDEX
    Explanations

    guilt-tripping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elementów
    1.06
     polypropylene
    0.96
     është
    0.94
     komponen
    0.93
     আসনের
    0.92
    Austria
    0.92
    Á
    0.92
    Š
    0.91
     tersedia
    0.91
     MgO
    0.91
    POSITIVE LOGITS
     an
    0.81
     any
    0.80
     Nice
    0.76
     Best
    0.76
     Next
    0.76
     next
    0.73
     Any
    0.72
     Ideal
    0.72
    一个
    0.72
     worst
    0.71
    Act Density 0.010%

    No Known Activations