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

    Neuronpedia

    INDEX
    Explanations

    surface properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ږئ
    0.52
    শংস
    0.50
     Rajya
    0.49
     bun
    0.48
    いました
    0.47
    )^\
    0.46
    ContextHeader
    0.46
     הה
    0.45
     أيضاً
    0.45
    لي
    0.44
    POSITIVE LOGITS
     surface
    1.06
    Surface
    0.98
     Surface
    0.95
     surfaces
    0.92
    surface
    0.87
     поверхности
    0.82
     SURFACE
    0.81
     povr
    0.80
    flächen
    0.79
     सरफेस
    0.79
    Act Density 0.153%

    No Known Activations