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

    Neuronpedia

    INDEX
    Explanations

    equality or difference comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পাবার
    0.42
     кушымта
    0.38
    лери
    0.38
    varnothing
    0.38
    ^{+},
    0.38
    絡
    0.38
     definir
    0.37
     মিত্র
    0.37
    Brother
    0.37
    ';"+
    0.37
    POSITIVE LOGITS
     identical
    1.06
     comparing
    1.05
    comparing
    1.02
     compares
    0.98
    identical
    0.96
     compare
    0.96
    Comparing
    0.93
    compare
    0.92
     Comparing
    0.91
     equals
    0.90
    Act Density 0.042%

    No Known Activations