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

    Neuronpedia

    INDEX
    Explanations

    natural environment and beauty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ку
    0.78
    يا
    0.76
    م
    0.73
     данные
    0.73
     термина
    0.72
    м
    0.72
    માં
    0.71
     ahorrar
    0.71
     один
    0.69
     обслуживание
    0.68
    POSITIVE LOGITS
    us
    1.16
    a
    0.96
    o
    0.93
     can
    0.88
     Natural
    0.87
    aren
    0.84
    p
    0.83
    r
    0.80
    in
    0.78
     it
    0.77
    Act Density 0.028%

    No Known Activations