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

    Neuronpedia

    INDEX
    Explanations

    single, one, unified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comparing
    0.75
    comparing
    0.71
     comparison
    0.69
     comparisons
    0.66
    rapolation
    0.64
     comparación
    0.64
     agendas
    0.64
    comparison
    0.64
    協助
    0.64
     compares
    0.63
    POSITIVE LOGITS
     unified
    2.14
     single
    2.02
    single
    1.92
    单一
    1.88
    Unified
    1.85
    Single
    1.84
     еди
    1.84
    unified
    1.83
     하나의
    1.80
     ஒரே
    1.77
    Act Density 0.567%

    No Known Activations