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

    Neuronpedia

    INDEX
    Explanations

    small size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     大型
    0.62
    Large
    0.55
     LARGE
    0.55
    大型
    0.54
     large
    0.53
     ใหญ่
    0.52
     Large
    0.52
     brute
    0.49
    LARGE
    0.49
     hefty
    0.49
    POSITIVE LOGITS
     small
    1.71
     smaller
    1.70
     pequeña
    1.59
    small
    1.58
     pequeño
    1.56
     pequeñas
    1.55
     piccole
    1.54
     Smaller
    1.53
    Smaller
    1.52
     малень
    1.51
    Act Density 1.809%

    No Known Activations