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

    Neuronpedia

    INDEX
    Explanations

    array/object property access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.05
    ()");
    1.00
     '*',
    0.96
    𝚊
    0.94
     '/',
    0.93
    >):
    0.92
    )]:
    0.90
    ...");
    0.90
    \}=\
    0.89
    ?”,
    0.87
    POSITIVE LOGITS
    Une
    0.82
     पहल
    0.77
    reif
    0.75
     eleg
    0.73
     aff
    0.72
     secretory
    0.71
     Eleg
    0.69
     पृथ
    0.69
     proches
    0.68
     procure
    0.68
    Act Density 0.159%

    No Known Activations